SearchStack

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It correctly identifies the operation as a read ('Retrieves'), but does not disclose any behavioral traits such as required permissions, potential side effects (none expected), or limits (e.g., what happens if account not found). While the simplicity of the tool mitigates the need, a bit more detail would be beneficial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (one sentence, 7 words) and front-loaded with the verb 'Retrieves'. Every word contributes to the meaning without redundancy. Perfect length for a simple getter tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description does not explain what 'details' entails (e.g., fields returned, format). For a simple account retrieval, this might be acceptable, but with many sibling tools, more context about the return structure would aid selection. The description is minimally complete but leaves ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds the phrase 'by name' reinforcing the parameter's purpose, but does not provide additional insights beyond what the schema already states ('Name of the Account'). No enrichment of parameter meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Retrieves'), the resource ('details of an Account'), and the specific method ('by name'). It distinguishes from siblings like account_get_name which might use a different identifier, though that sibling's purpose is not fully known. The verb+resource+method combination is specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like account_get_name or other retrieval tools. There is no mention of prerequisites, context, or when not to use it. The description lacks any usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, so description carries burden. States it is a retrieval operation, but does not disclose that it requires no parameters, is safe, or has no side effects. Adequate but minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no wasted words, direct and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema provided; description does not specify return format (e.g., plain string or object). Could mention that it returns just the name string.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters, and schema coverage is 100%, so description adds no extra info. Baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb 'Retrieves' and resource 'account name' for the currently authenticated API key. Distinguishes from sibling 'account_get' which likely returns more data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use guidance. Usage is implied but not compared to alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must fully disclose behavioral traits. It implies a read-only operation ('Search analytics') but does not explicitly state that no data is modified. It also does not mention authentication requirements, rate limits, or potential side effects. The date format and default are helpful, but overall transparency is adequate yet incomplete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences: the first states the core purpose and outcome, the second adds necessary parameter detail. No redundant words or filler; every sentence serves a purpose. It is well-structured and front-loaded with the most critical information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the moderate complexity (4 parameters, no output schema, no nested objects), the description covers the essential aspects: the data returned, date range handling, and default behavior. It does not explain the return format (since no output schema exists), but it provides enough context for an agent to understand what the tool does and how to use it. For a straightforward analytics retrieval, this is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value beyond the schema by specifying date format ('yyyy-MM-dd') and default behavior ('defaults to the last 30 days when omitted'). This clarifies the usage of 'from' and 'to' parameters beyond their schema description. The required parameters 'accountName' and 'groupName' are not further elaborated, but the added date context elevates the score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Search analytics' for a specific resource 'a Group', listing the exact metrics returned (total searches, zero-result searches, etc.). This distinguishes it from sibling tools like 'analytics_get_list' which likely returns a list of analytics. The purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies the tool is for analytics over a UTC date range and states the default behavior (last 30 days when omitted). However, it does not provide explicit guidance on when to use this tool vs alternatives like 'analytics_get_list', nor does it mention any prerequisites or exclusions. Strong usage context but lacks comparative guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the date format, default range (last 30 days), and scope of data (list, UTC range). It implies read-only analytics without stating permissions, but for a simple query tool this is sufficient. It does not mention rate limits or side effects, but none are expected.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no wasted words. The first sentence front-loads the main purpose and outputs, and the second adds the date format and default. This is ideal for agent consumption.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description lists the key return values (total searches, zero-result searches, click-through rate, top searches, top zero-result searches). This is adequate for understanding what the tool returns. It could mention the structure of the response (e.g., objects with keys), but for a list of metrics it is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with each parameter described in the schema. The description adds value by explaining the date format ('yyyy-MM-dd') and default behavior ('defaults to the last 30 days when omitted'), which is not in the schema. This enhances understanding beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches analytics for a List over a date range, listing specific metrics (total searches, zero-result searches, click-through rate, top searches, top zero-result searches). The verb 'Search' and the resource 'analytics for a List' are precise, and it is easily distinguished from the sibling tool analytics_get_group.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a use case: 'Useful for finding zero-result queries to improve.' This provides clear context for when to use the tool. However, it does not explicitly mention when not to use it or alternatives (like analytics_get_group for group analytics), which would make it a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavior. It does not specify whether the operation appends or replaces, permissions required, rate limits, or whether it's asynchronous. For a bulk mutation tool, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, direct and without filler. Every word is informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema or annotations, the description could explain return values, success indicators, or error conditions for a bulk operation. It provides minimal but adequate information for a simple use case.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds context by clarifying that the 'listName' must correspond to an existing list and that items are free-form dictionaries. This adds meaning beyond the schema's basic string descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it bulk inserts search results into an existing list, specifying that each item is a free-form field dictionary matching the list's fields. This differentiates it from the sibling 'bulk_insert_with_fields' by implying flexible field matching.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the list must exist but does not explicitly state when to use this tool versus alternatives like 'bulk_insert_with_fields' or other insert tools. No when-to-use or when-not-to-use guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must fully disclose behavior. It mentions inserting and creating missing fields, but the lack of a dictionary parameter in the schema undercuts trust. No information about side effects, permissions, or return values is provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and to the point, but it omits critical details about the parameters and how the dictionaries relate. Conciseness is positive, but structural clarity is lacking.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (bulk insert with field creation) and lack of output schema, the description is incomplete. The agent lacks information about what dictionaries should be provided and how the tool behaves, making it hard to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: both parameters have descriptions, so the baseline is 3. However, the description does not add meaning beyond the schema and actually refers to 'dictionaries' not present in the schema, creating confusion. This reduces the score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Bulk insert Search Results' which gives a verb and resource, but the addition 'also creating any missing fields from the supplied dictionaries' is not reflected in the input schema, making the purpose ambiguous. The sibling 'bulk_insert' suggests this variant adds field creation, but the schema lacks a dictionary parameter.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit or implicit guidance on when to use this tool vs siblings like 'bulk_insert'. The description does not differentiate usage context, nor does it mention prerequisites or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description carries the full burden. It adds context about contributor permissions but lacks details on prerequisites, idempotency, or error scenarios.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with no unnecessary words, front-loading the action and quickly adding value with permission context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple add tool, the description covers the core purpose but lacks details on return values, error cases, and prerequisites, which would be expected given the absence of annotations and output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the descriptions are minimal. Parameter names are self-explanatory, but the tool description adds no further details on formats or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Add a Contributor' (verb+resource) and explains what a Contributor can and cannot do, distinguishing it from sibling tools like contributors_delete.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It specifies when to use the tool (to add a contributor) and describes the contributor's capabilities, but does not explicitly mention when not to use or provide alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It only states 'Remove' without indicating permanence, required permissions, or side effects. This is insufficient for a potentially destructive operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words. However, it lacks structure (e.g., bullet points) and could benefit from a bit more detail without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (3 required params, no output schema), the description is minimal but missing important context: what happens on successful removal, error cases, and whether removal is reversible. The absence of output schema heightens the need for such context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter has a basic description ('Name of the ...'). The tool description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Remove') and the resource ('a Contributor from a List'). It differentiates from sibling tools like contributors_create (add) and coordinates_delete (different resource).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use or not use this tool. No prerequisites, contextual cues, or alternatives mentioned. The description does not address deletion constraints (e.g., contributor existence, permissions).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must fully disclose behavioral traits, but it only states the action without explaining side effects, permissions, or the state of the list after the operation. It does not indicate if the tool is destructive or idempotent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, succinct sentence that efficiently communicates the core purpose. However, it could be slightly more structured by adding a second sentence for usage context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 parameters, no output schema, no annotations), the description is too brief to be complete. It fails to explain the nature of the Coordinates field, data format, or any constraints, leaving significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100% and parameters have brief descriptions, the tool description adds no additional meaning beyond what is in the schema. The baseline for full coverage is 3, so this score is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Add a Coordinates field') and the target resource ('a List'), and mentions the benefit ('enabling geographical queries'). It is specific and distinguishes from the sibling tools, especially coordinates_delete.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions. For example, it doesn't indicate whether the list must already exist or if coordinates can be added multiple times.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must bear full weight. It discloses the breaking change and version bump, which is important for understanding the destructive nature. However, it does not detail other behaviors (e.g., irreversibility, impact on dependent data).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two brief sentences, no extra words. Every sentence adds value: the action and the breaking change warning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple deletion tool with no output schema and only two parameters, the description is fairly complete. It explains the action and a key side effect (version bump). Missing details like prerequisites or return type, but not critical for this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters. The tool description adds no extra meaning beyond the schema, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Remove') and the resource ('Coordinates field from a List'), and the phrase 'Breaking change: bumps the List version' adds specificity. It distinguishes itself from siblings like coordinates_create by focusing on deletion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., list_edit or coordinates_create). It does not mention prerequisites, constraints, or when not to use it. The only context is the breaking change note.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses asynchronous nature and that it returns a run_id and cost estimate. However, it does not cover side effects, permissions required, or error conditions (e.g., nonexistent account/eval set).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no redundant information. Efficiently communicates the core purpose and return value. Well-structured and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter async tool with no output schema, the description is fairly complete: it explains the high-level process, the return value (run_id + estimate), and the follow-up action (poll with EvalRunStatus). Could benefit from mentioning prerequisites like existing eval set, but overall sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with basic descriptions for accountName and evalSetName. The tool description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool starts an asynchronous eval run, explaining verb ('Start') and resource ('eval run'). It details the process (search against pinned records, scored by judge) and distinguishes from sibling tools like eval_run_status by mentioning polling with a run_id.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (start run, then poll with EvalRunStatus) but lacks explicit guidance on when to use this tool versus alternatives like eval_run_history or eval_set_bootstrap. No 'when-not-to-use' or prerequisites are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so description carries full burden. It describes the tool as read-only ('Get'), mentions pagination and ordering, but does not disclose error handling, authentication needs, or side effects. Adequate but missing some behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with key information, no unnecessary words. Efficiently communicates purpose, ordering, and pagination.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but description does not explain return values beyond 'score history'. It mentions ordering and pagination but lacks details on response structure, limiting completeness for an agent without prior knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear parameter descriptions. The tool description adds no additional parameter-level information beyond what the schema provides, so baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Get an eval set's score history', specifying the verb and resource. It distinguishes from siblings like eval_run and eval_set_view by focusing on score history rather than running or viewing set details.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates when to use: to retrieve score history sorted newest first. It does not explicitly state exclusions, but the context is clear and sibling tools are sufficiently different for an agent to infer appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses that it polls (read operation) and returns specific data, but does not discuss error behavior, idempotency, or required permissions. The transparency is adequate but not thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single 22-word sentence, front-loaded with the verb and resource, and every phrase adds value. No waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately explains the return contents (status, environment, tallies, per-query rows). It does not mention possible status values or error cases, but for a polling tool with simple parameters, it is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all three parameters, but the descriptions are minimal (e.g., 'Id of the eval run to poll.'). The tool description adds no extra meaning beyond the schema, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'poll' and resource 'eval run', and clearly enumerates the returned data (lifecycle status, environment, tally counts, rates, per-query rows). It adequately distinguishes from siblings like eval_run (which starts runs) and eval_run_history (which lists runs), though not explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. The description implies polling after run creation, but does not state prerequisites, when not to use, or link to related tools like eval_run or eval_run_history.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It describes the core behavior (replaying searches, taking pinned elements) and a skip condition, but does not clarify side effects (e.g., whether the operation is read-only or creates new records), auth requirements, or error handling. Some behavioral gaps remain.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured paragraph that front-loads the action and key constraints. It is dense but efficient, with no irrelevant details. Could be slightly more streamlined but is already concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description covers the purpose and input constraints but omits details about the output (the created eval set), prerequisites (existence of prior runs), error conditions, and what happens if constraints are violated. Feels incomplete for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% description coverage, providing clear definitions for request and accountName. The tool description adds extra context, e.g., explaining that source_run_ids are 'of the judge runs to seed queries from' and that context fields are for the judge ideal. This enriches the schema's meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it bootstraps an eval set from prior retrieve-then-judge runs, clearly distinguishing it from other eval set tools like eval_set_create. It specifies the mechanism (replay search, take pinned target/judge) and a constraint (skip runs with explicit candidates).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use this tool (to create eval sets from existing runs), what is skipped (judge runs with explicit candidates), and a precondition (all source runs share one target and judge). It lacks explicit mention of alternatives but the context is clear from sibling names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It explains that the version is frozen to a concrete number and that pinning fixes which records are searched but not the results (live at runtime). This adds significant behavioral context beyond a simple 'create' action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences front-loaded with the verb. Every sentence provides essential information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the key pinning behavior and the schema covers required fields, but it does not describe the output or return value. For a creation tool, it would be helpful to mention what the response contains (e.g., the eval set ID).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, so the baseline is 3. The description adds context about pinning and frozen versions but does not elaborate on individual parameters beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create an eval set' with the specific verb 'Create' and resource 'eval set'. It further specifies 'against a pinned list/group version', which differentiates it from other eval set tools like eval_set_bootstrap or eval_set_view.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for creating eval sets pinned to a specific list or group version, but it does not provide explicit guidance on when not to use it or mention alternative tools. No exclusions or context for selection are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description explicitly discloses the cascading destructive behavior (deleting runs and per-query rows). This adds transparency beyond the basic delete operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is front-loaded with the action and cascade detail. No extraneous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter delete tool without output schema, the description sufficiently explains the action and its scope. The cascade detail provides necessary context about side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with simple descriptions for accountName and evalSetName. The tool description adds no additional semantic value beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies a clear action ('Delete') on a specific resource ('eval set') and mentions the cascading effect on runs and rows. This distinguishes it from sibling tools like eval_set_create or eval_set_list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for deletion but provides no explicit guidance on when to use this tool vs alternatives, nor any prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description must fully convey behavioral traits. It identifies a read operation ('List') and defines the domain concept, but does not disclose details like pagination, error handling, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences efficiently communicate the tool's purpose and the key concept of an eval set. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, list operation) and no output schema, the description adequately covers the necessary information. However, it omits mention of pagination or ordering, which could be relevant for list endpoints.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter 'accountName' is described in the schema as 'Name of the Account.' The description reinforces that the tool operates on an account, but adds no new meaning beyond the schema. Since schema coverage is 100%, baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List' and the resource 'eval sets' for an Account. It also defines 'eval set' to ensure understanding, and distinguishes it from siblings like eval_set_create or eval_run which have different actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as eval_set_view or eval_run. No explicit context for usage or exclusions is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. The use of 'Get' implies a read-only operation, but it does not explicitly state no side effects, auth requirements, or rate limits. The description is minimally adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that conveys the tool's purpose without redundancy. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description lists the configuration components, giving the agent a good idea of the return value. With two simple parameters, this is largely sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents both parameters. The description does not add any additional meaning or constraints beyond the parameter names, which are self-explanatory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves an eval set's configuration, listing specific components (pinned target, judge, context, query cases). This distinguishes it from sibling tools like eval_set_list (listing) and eval_set_bootstrap (initialization), though not explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description does not mention exclusions, prerequisites, or conditions under which eval_set_view is preferred over other tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must fully disclose behavioral traits. It only describes the function and a prerequisite, but does not mention side effects, authentication requirements, rate limits, or whether it is read-only or destructive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, each serving a purpose: one for the main action and one for a critical usage condition. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description does not explain what the extracted text looks like or how it is returned. It also does not cover edge cases like missing PDFs or multiple PDFs. The MaxDocumentPages condition is helpful but incomplete context for a tool with no return value documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides descriptions for all three parameters (100% coverage), so the description adds no additional parameter meaning. Baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool extracts text from PDF documents attached to a Search Result, using specific verbs and resources. It distinguishes itself from sibling tools like search_result_* which manage search results but do not extract PDF text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear condition for usage: 'Only available when the List's model declares a positive MaxDocumentPages limit.' This guides agents on prerequisites. However, it does not explicitly state when not to use this tool or suggest alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description lacks behavioral details such as whether the operation is idempotent, what happens if the Facet already exists, or any side effects. With no annotations, the description should compensate but fails to do so.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise, consisting of one sentence and a brief definition. No extraneous words, but it could be slightly longer to include more useful context without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with a nested required parameter and no output schema or annotations, the description is insufficient. It does not explain error conditions, return values, or the full context of use, leaving gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter is documented in the schema. The description adds no extra meaning beyond that, achieving the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Create a Facet.' and defines a Facet as a filterable field. It distinguishes from sibling tools like facet_remove, facet_rename, and facet_values by focusing on creation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives or prerequisites. The description does not mention that an existing Account and List are required, nor does it specify conditions for creating a Facet.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description mentions a key behavioral trait: 'Breaking change: bumps the List version.' This adds value beyond the bare action, but lacks details on destructive nature, permissions, or reversibility. Since no annotations exist, the description partially fulfills the transparency need.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences, front-loading the main action and adding only one essential behavioral detail. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple mutation tool with 3 parameters and no output schema, the description is minimally adequate but lacks context about permanence or side effects beyond version bumping. It could mention that removal is permanent or require specific permissions, leaving some gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and each parameter has a description, so the schema already explains the parameters. The description adds no additional meaning beyond the schema, warranting the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Remove a Facet,' using a specific verb and resource. This distinguishes it from sibling tools like facet_create and facet_rename, which have different actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or exclusions, leaving the agent without decision support.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that renaming is a breaking change that bumps the List version, providing important behavioral context not captured in the schema. No annotation contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short, front-loaded sentences with no filler. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has fully described schema and no output schema. The description adds the breaking change note, which is useful. However, it doesn't mention reversibility or side effects beyond version bump.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds no extra meaning beyond the schema's parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Rename an existing Facet', specifying the verb and resource. It distinguishes from sibling tools like facet_create and facet_remove.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs alternatives. Usage is implicit from the operation name, but no context or prerequisites are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. States it is a read operation (listing values) and requires a specific permission. No mention of destructive side effects, which is consistent with a read-only tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no redundancy. Front-loaded with core purpose, then usage context and permission. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity, no output schema, and full schema coverage, the description is complete. It covers purpose, use case, permission, and the tool's role in the search workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds minimal extra meaning beyond schema; the phrase 'on a List version' and 'name of the Facet' are already implied by parameter names and descriptions. The cache parameter is self-explanatory from schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it lists distinct values of a Facet on a List version, with explicit use case for building filter UIs. Distinguishes from sibling tools like facet_create and facet_remove.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly mentions usefulness for building filter UIs and required permission (search-result:read). Provides context for when to use, though no explicit when-not-to-use or alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; the description reveals the output includes links but does not disclose behavior such as read-only nature, authentication requirements, or potential side effects. With no annotations, the description carries the full burden but provides only basic outcome information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with 17 words. Every word contributes meaning, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no output schema, the description adequately states what it does and what it returns. Could mention if the catalog is comprehensive or filtered, but the specification 'Public API discovery catalog' is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so schema coverage is 100% trivially. The description adds value by specifying what the return contains (links), which goes beyond the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the direct object 'Public API discovery catalog', including what it contains (links to OpenAPI, docs, manifest, examples). This distinguishes it from sibling tools like get_api_info and get_examples.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (call to retrieve catalog) but does not explicitly state when to use it vs alternatives, nor any prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It adds behavioral context by stating it should be called once per session, but does not explicitly state it is read-only or describe any side effects. Minimal but adequate transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the key action and includes a usage guideline. Every part is necessary and no words are wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters, no output schema, and no annotations, the description is fairly complete: it specifies what the tool returns and how often to call it. It could mention HTTP method or response format, but for a simple manifest retrieval it is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so schema description coverage is 100%. No parameter documentation is needed, and the description does not add any parameter semantics—none required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get', the resource 'Public API self-describing manifest', and the content (auth, error codes, MCP integration guidance). This distinguishes it from sibling tools, none of which appear to provide a manifest.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Call once per session', providing clear usage guidance. It does not mention when not to use or alternatives, but the unique purpose makes this less critical.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It indicates the tool is read-only (getting examples) and that examples are curated, but does not disclose caching, rate limits, or whether examples are static or dynamic. Adequate for a simple retrieval but lacks depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence with no wasted words. It conveys the essential purpose efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (zero parameters, no output schema), the description is mostly complete. It states what the tool retrieves, though it could specify the scope of examples (e.g., all endpoints) for better completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so the description does not need to add parameter info. Schema coverage is 100% vacuously, and with 0 parameters, the baseline is 4. The description adds no parameter details because there are none to explain.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool gets a curated library of worked request/response examples for the Search Stack Public API. It uses a specific verb and resource, and distinguishes itself from sibling tools like get_api_catalog or get_api_info which serve different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives is provided. The description does not mention when-not-to-use or any usage context, leaving the agent to infer from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. Description only states the operation without disclosing behavioral traits like duplicate handling, validation, or permissions required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no filler, appropriately sized for a simple operation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Missing information about return values, error cases, and prerequisites (e.g., group existence). Incomplete for a mutation tool with no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with basic descriptions. The tool description does not add new meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Add an IP address to a Group's access whitelist', specifying a specific verb and resource, and distinguishes from sibling tools like group_remove_ip_address.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives. Implicit from name but no explicit context about prerequisites or exceptions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description must disclose behavioral traits. It only implies mutation but does not mention side effects, requirements, or what happens to existing data. Minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Very concise single sentence with no wasted words. However, it could be more informative without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given three parameters including a nested object and no output schema, the description is too minimal. It does not explain parameters like adapt_to_first_list, version semantics, or return value, leaving significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%; all parameters have descriptions. The tool description adds 'at a version' which is already implied by the version parameter. No additional semantic enrichment beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (add), the resource (List) with a qualifier (at a version), and the target (Group). It distinguishes from sibling tools like group_remove_list or group_get.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, prerequisites, or scenarios where it should not be used. The description only states what it does without usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses the no-op condition, but does not mention required permissions, error behavior for missing groups, or side effects beyond re-pinning lists. This is adequate but not thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the action, and contains no extraneous information. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two string parameters and no output schema, the description covers the core functionality and edge case (no-op). It could mention return values or error handling, but given the low complexity, it is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with basic descriptions ('Name of the Group', 'Name of the Account'). The description adds no additional meaning or context for the parameters, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('bump a group's version') and the mechanism ('re-pins every member List to its latest version and advances current_version'). It also notes the no-op case, distinguishing it from sibling tools like group_edit or group_restore_version.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the description (when you need to advance a group's version), but there is no explicit guidance on when to use this tool versus alternatives like group_edit or group_restore_version. No when-not or prerequisite information is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description discloses key behaviors (copying config and members, default pin_latest) but omits whether the source is modified or what authorization is needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded, no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Lacks output schema or description of return value, and does not mention prerequisites like existence of source group.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers all 3 parameters with descriptions; the description adds minimal extra meaning beyond the existing metadata.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool clones a group, copying configuration and member lists, with a default behavior of re-pinning. It distinguishes from siblings like group_create or group_edit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what the tool does but does not provide explicit guidance on when to use it over other group tools or when to avoid it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It only says 'Create a Group' without mentioning side effects, permissions, or what operations are implied. This is insufficient for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the verb and resource, and every sentence provides value. There is no extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the operation (creating a group that requires existing lists, subscription, account), the description does not cover prerequisites, relationship to other tools (like group_add_list), or return behavior. Lack of output schema further reduces completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool description adds no meaning beyond the input schema. The nested fields (model_name, reranker_name) are not explained, and the schema itself lacks descriptions for these fields despite 100% coverage referring only to the top-level parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'Create' and the resource 'Group', and explains what a Group is ('combines multiple Lists for cross-list searching'). It effectively distinguishes this tool from sibling tools like group_edit or group_delete.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, nor any prerequisites or limitations. With many group-related siblings, explicit usage context is missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries full burden. It only says 'Remove a Group' without disclosing whether the action is permanent, reversible, requires permissions, or has cascading effects. The tool is clearly destructive, but no safety or side-effect information is given.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, consisting of a single 3-word sentence. It is front-loaded and has no wasted words, but it may be too minimal to be maximally helpful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's destructive nature, lack of output schema, and no annotations, the description is insufficient. It does not explain return values, effects, or prerequisites, leaving the agent with incomplete information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both parameters described in the schema. The description does not add any additional meaning beyond what the schema provides, but it does not need to because the schema is self-sufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Remove a Group.' clearly states the verb and resource, but it essentially restates the tool name. It is not misleading and differentiates from many sibling tools, though it does not explicitly distinguish from related deletion tools like group_remove_ip_address.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no indication of prerequisites, when not to use it, or how it differs from other group deletion tools among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description bears full responsibility for behavioral disclosure. It merely states the action ('edit') without revealing side effects, authorization needs, immediacy of changes, or impact on group versions. This is insufficient for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence (12 words) that front-loads the verb and key resource. There is no redundancy or wasted text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 3 parameters, no output schema, and no annotations, the description is too brief. It fails to explain return values, preconditions (e.g., group existence), or post-edit behavior, which are critical for correct usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description aligns with the schema's parameters but adds no extra semantic information beyond summarizing which fields are editable. It does not elaborate on constraints, relationships, or usage details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Edit' and clearly identifies the resource as 'a Group's default search/suggest size and distance unit.' This distinguishes it from sibling tools like group_create, group_delete, and group_set_model, which serve different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool vs. alternatives (e.g., group_set_model, group_bump_version). There is no mention of prerequisites, conditions, or situations where this tool is inappropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden. It only lists what data is retrieved but does not disclose any side effects, error behavior, or permissions required. This is insufficient for a read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 10 words, front-loaded with the action. No redundant information, every word serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple get tool with no output schema, the description mentions all key returned components (configuration, member lists, IP whitelist). It lacks error handling or permission notes but is mostly complete for typical usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (both parameters have descriptions). The tool description adds no additional meaning beyond the schema, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Get') and resource ('Group'), and specifies what aspects are retrieved (configuration, member Lists, IP whitelist). This distinguishes it from other group operations like create, delete, or edit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives (e.g., other group-related tools). The purpose is implied but no exclusions or context are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states what the tool retrieves (member lists, pinned versions) without mentioning side effects, permissions, error states, or data scope. This is insufficient for a retrieval tool with no annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, but it is poorly structured and contains ambiguous wording ('searches'). While short, it sacrifices clarity for brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema and the simplicity of the tool (3 required parameters, no nested objects), the description provides a vague idea of the return value (member lists, pinned versions) but lacks details on structure or how these relate to the input parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the parameter descriptions are clear. The tool description adds no extra meaning beyond what the schema provides, such as format constraints or relationships between parameters. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Get the member Lists (and pinned versions) that a specific group_version searches.' It identifies the resource (member lists and pinned versions of a group version) and the action (get). However, the phrasing 'searches' is ambiguous and doesn't clearly differentiate from sibling tools like group_get or group_get_versions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. Among many group-related siblings, the description provides no context for selection, such as prerequisites or scenarios where this tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It indicates a read operation without side effects, but does not disclose return format, ordering, pagination, authentication requirements, or rate limits. The behavior beyond listing is opaque.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core purpose, followed by a usage hint. No extraneous words. Efficient and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with no output schema, the description conveys the main function and a key usage hint. However, it omits details about the return value (e.g., version IDs) and does not fully leverage context from sibling tools to differentiate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions 'Name of the Group.' and 'Name of the Account.' The description does not add further meaning to these parameters; baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'List every searchable membership version of a Group' which clearly identifies the verb and resource. It is distinct from sibling tool 'group_get_version_members' which gets members of a specific version, but this differentiation is implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The second sentence provides a usage hint: 'Pass one as group_version to search a frozen set of records.' However, it does not explicitly state when to use this tool versus alternatives like 'group_get_version_members' or 'group_get', nor does it mention when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the transparency burden. It states the removal action but does not disclose side effects, idempotency, or required permissions. The action is straightforward, so score is moderate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no wasted words. Highly concise and to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (remove an IP), the description adequately covers the action. However, lack of output schema or mention of return value/error states leaves minor gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all three parameters. The description adds no additional meaning beyond the schema, so baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'Remove' and the resource 'IP address from a Group's access whitelist,' providing a specific verb and resource. It naturally distinguishes from siblings like group_add_ip_address.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives (e.g., group_add_ip_address). No prerequisites or when-not-to-use context provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It does not disclose if the operation is irreversible, requires permissions, or what happens to associated data. Only the basic removal is stated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single efficient sentence but too brief; it could include more context without becoming verbose. It is front-loaded but barely meets the minimal information threshold.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema or details about return values or side effects. Given the tool's simplicity, it lacks completeness for an agent to understand the full impact of the operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds no extra meaning beyond the schema's parameter descriptions, which are minimal but sufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Remove') and resources ('List from a Group'), making the purpose unambiguous. It does not distinguish from sibling tools like 'group_remove_model' but those target different resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like 'group_add_list' or other group removal tools. The description lacks context about prerequisites or conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must bear the burden. It adds the effect ('reverting it to keyword search') but lacks details about prerequisites, side effects, or required permissions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 14 words, directly stating the action and effect with no extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple removal tool with two well-documented parameters, the description covers the essential information (action and outcome) and is complete given the context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters. The description does not add additional meaning beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Remove') and identifies the resource ('embedding model from a Group'), and distinguishes from siblings like group_set_model by stating the reversal effect ('reverting it to keyword search').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for removing a model, but does not explicitly state when to use vs alternatives, nor does it provide exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It mentions reverting to score-based ordering but lacks details on side effects, prerequisites, or whether action is reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no wasted words, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Simple tool with 2 required params and no output schema; description sufficiently covers purpose and outcome. Could mention return value but not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema provides 100% coverage for parameters with brief descriptions. Description adds no extra parameter meaning beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verb 'detach' and resource 'reranker from a Group', clearly stating it reverts to score-based ordering. Distinguishes from sibling group_set_reranker.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied (when you want to remove reranker), but no explicit when-to-use or when-not-to-use instructions. No alternatives mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description discloses key behavioral traits: restoration is roll-forward (not destructive rewind), and member lists deleted since that version are skipped and returned. However, it omits details like permissions, reversibility, and full output structure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences totaling 26 words, front-loaded with purpose and behavioral nuance. Every sentence adds value with no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity and lack of output schema, the description covers the core action and a key edge case (skipped lists). It is mostly complete for a 3-parameter tool but could mention prerequisites or effects on other group properties.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with basic descriptions for all three parameters. The tool description adds overall behavior context but does not enhance parameter-level meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool restores a historical membership version as the new current_version, with specific verb+resource, and distinguishes from siblings by specifying 'roll-forward, not rewind' and mentioning skipped lists behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (restoring a historical version) but does not explicitly state when to use this tool versus alternatives like group_bump_version or group_clone. No when-not or exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of behavioral disclosure. It only reveals that hits include list_name and that both free-text and vector search are supported, but it omits important behaviors like pagination, caching, or how queries combine with vector search. The parameter descriptions in the schema cover details, but the description itself lacks transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, consisting of two short sentences that are front-loaded with the core action and a key output feature. Every word earns its place, with no redundancy or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description does not explain the return structure beyond listing list_name in hits. For a complex tool with 16 parameters, the description lacks completeness about what the search returns, how results are sorted, or the behavior of the version parameter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Since the schema covers 100% of parameter descriptions, the baseline is 3. The description adds minimal meaning beyond the schema, only hinting at the use of query and vectorSearch parameters through the phrase 'free-text and/or vector search'. This does not significantly enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool performs free-text and/or vector search across a Group of Lists, which distinguishes it from single-list search tools like search_list or suggestion tools like suggest. It also mentions that hits include list_name, adding specificity to the output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as group_search_post or search_list. The description does not include conditions or exclusions, leaving the agent without clear decision criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does not mention any behavioral traits such as read-only nature, side effects, authentication requirements, rate limits, or whether the search is state-changing. The description only states the action, missing critical transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a concise single sentence that efficiently communicates the core action and variant. It is front-loaded with the purpose, but lacks structured sections. Still, it earns its place without verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the tool (nested SearchOptions with many subparameters, no output schema), the description is too brief. It does not explain what the tool returns, how results are structured, or how to handle pagination. The agent may need additional documentation to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are well-documented in the schema. The description only adds that it accepts a SearchOptions body, which is already clear from the schema's 'options' parameter. No additional meaning beyond the schema is provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as performing free-text and/or vector search across a Group of Lists, and explicitly notes it is a POST variant. This distinguishes it from sibling tools like group_search (likely GET) and other search variants.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies it should be used when a POST request with a SearchOptions body is needed, but does not provide explicit guidance on when to choose this over alternatives like group_search, suggest_post, or other search tools. No when-not-to scenarios are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses the asynchronous re-embedding side effect. With no annotations, the description partially covers behavioral traits but lacks details on permissions, destructiveness, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no fluff. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the basic purpose and a key side effect. Lacks details on error handling, status checking, or what happens if model is invalid.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description does not add additional meaning about parameter values, formats, or valid choices for model_name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Set the embedding model for a Group.' It also mentions the asynchronous re-embedding of Member Lists, which distinguishes it from siblings like group_remove_model or group_set_reranker.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. Does not mention prerequisites (e.g., group existence) or scenarios where this tool is inappropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must fully disclose behavioral traits. It only states 'attach' without explaining overwriting behavior, permission requirements, side effects, or idempotency. Inadequate for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that efficiently conveys the action. However, it is not structured with additional context; appropriate length but lacking details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 required parameters, a nested object, and no output schema or annotations, the description is too sparse. It fails to explain what happens after attachment, return values, or error conditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with basic descriptions. The tool description adds no extra meaning beyond what the schema provides, such as the format or constraints of the reranker string. Baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Attach a bring-your-own reranker to a Group.' clearly specifies the action (attach) and the resources (reranker and Group). It effectively distinguishes from sibling tools like group_remove_reranker.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as group_remove_reranker or group_set_model. Lacks context about prerequisites or scenarios where setting a reranker is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It mentions the permission requirement but does not describe side effects, error behavior, or output format. For a tool with no annotations, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the core purpose and a key requirement. No superfluous information; every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should explain what the tool returns (e.g., list of suggestions with matching fields). It also does not cover pagination or filtering behavior. Given the complexity of 8 parameters, the description is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains parameters. The description adds only the permission requirement, which is not parameter-specific. Thus, the description adds minimal extra value over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Typeahead suggestions across all Lists in a Group.' It also specifies the required permission, which adds clarity. This distinguishes it from sibling tools like 'suggest' and 'group_search'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for typeahead scenarios but does not explicitly state when to use this tool versus alternatives like 'suggest' or 'group_search'. No when/not-to-use guidance is provided, making it less helpful for selection decisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description does not disclose whether suggestions are read-only, whether the POST modifies state, or any other behavioral traits like idempotency or side effects. The description carries the full burden but lacks this context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with purpose, and each sentence adds value without redundancy. Efficient and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of 5 required parameters with a nested options object and no output schema, the description is too minimal. It lacks guidance on how to structure the options, what the return value looks like, and the meaning of 'typeahead' in context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with each parameter having a description. The description adds context about the options object being a 'SuggestOptions body', but does not explain parameter meanings beyond the schema, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides 'Typeahead suggestions across all Lists in a Group' and identifies it as a POST variant, distinguishing it from siblings like 'group_suggest' (likely GET) and 'suggest'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the POST variant is for sending a body (SuggestOptions), but does not explicitly state when to use it over the GET variant or provide alternatives. No when-not or preconditions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions transferring a group and its member lists but does not disclose whether the original group is deleted or moved, what permissions are required, or any side effects. This creates ambiguity for the agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that directly conveys the tool's action without unnecessary words. It is front-loaded and efficient, earning its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a transfer operation with nested parameters and no output schema, the description is incomplete. It does not explain what the tool returns, potential error conditions, or the exact effect on the source group. The agent is left with significant unknowns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with each parameter having a basic description. The tool's description adds minimal value beyond these, merely restating the overall action. The nested 'request' object's purpose is clear from the schema, but no additional semantic context is provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Transfer' and identifies the resource ('a Group and its member Lists') and the target ('a different subscription'). This clearly distinguishes it from sibling tools like group_create or group_clone, which have different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any guidance on when to use this tool versus alternatives such as group_clone or group_edit. It lacks explicit context about prerequisites or exclusions, leaving the agent to infer usage from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries full burden. It discloses that the API key is verified on create, but does not mention that it is a write operation, potential side effects, or that the judge can be deleted via judge_delete. Partial transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no wasted words. The first sentence clearly states the purpose, and the second adds a behavioral detail. Well-front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description lacks information about what is returned upon success (e.g., judge ID), required permissions, or rate limits. Given the complexity of the nested object and no output schema, more context would be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters. The description adds no additional meaning beyond the schema, such as clarifying the exact format of instructions or output_schema. Baseline score is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a bring-your-own LLM judge and explains its function as a post-search filter. It uses specific verbs and identifies the resource, distinguishing it from sibling tools like judge_delete and judge_run.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for creating a custom judge but does not provide explicit guidance on when to use it versus alternatives like judge_run or judge_try. No exclusions or context are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries full burden. It only says 'Delete' without disclosing whether the deletion is permanent, reversible, requires special permissions, or affects related data. This is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no fluff. It is appropriately concise for a simple delete operation, though it could benefit from minimal behavioral context (e.g., irreversibility).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a delete operation with no output schema, no annotations, and no additional context, the description is incomplete. It fails to convey whether the deletion is permanent or if any confirmation is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for both parameters. The description adds no additional semantics beyond the schema, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (delete) and the resource (a Judge). It distinguishes from sibling tools like judge_create and judge_list by the verb. However, it doesn't add any nuance beyond the name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives (e.g., judge_create for undeleting?), prerequisites, or side effects. The usage is only implied by the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions that secret API keys are omitted, which is a behavioral detail about the response. However, it does not explicitly state that the operation is read-only or idempotent, nor does it describe any edge cases like empty results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with the verb and object front-loaded. Every word is essential, and the parenthetical note adds value without creating verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with one parameter and no output schema, the description is largely complete. It states the function, the required parameter (accountName), and a key output detail (keys omitted). Could optionally mention that it returns a list of judges, but it is adequate as is.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (accountName described as 'Name of the Account'). The description adds no new information about the parameter beyond what the schema provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'list' and the resource 'bring-your-own LLM judges configured for an Account'. It distinguishes from sibling tools like judge_create and judge_delete by specifying the listing action. The note about omitted keys adds specific context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context with 'for an Account', but does not explicitly state when to use this tool vs alternatives. No exclusions or alternative recommendations are given, though siblings are clearly different operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the burden is on the description. It discloses that the run is asynchronous and returns a run_id, but it does not mention side effects, authentication needs, or error conditions. More detail would improve transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the action, and contains no extraneous words. It efficiently conveys the core purpose and return flow.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (3 required params, nested objects, no output schema), the description explains the async pattern and the return of a run_id. It omits details about the request body structure, which are covered by the schema, so overall it is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The tool description does not add additional semantic detail beyond what the schema provides for each parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it starts an asynchronous batch Judge run over a candidate set, using specific verbs and resources. It distinguishes from siblings like judge_run_status and judge_try by indicating it's an async start.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains that it returns a run_id to poll with JudgeRunStatus and that results are produced off the request path, indicating when to use it. However, it does not explicitly list alternatives or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the polling behavior and returns, implying read-only operation, but does not detail error handling, rate limits, or behavior if the run is not found. With no annotations, some transparency is present but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the action and return data using a colon-separated structure. It is concise without being overly terse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple polling function, the description adequately explains the return values (status, tally, per-candidate verdicts) despite lacking an output schema. It does not cover error conditions, but the core functionality is clear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the baseline is 3. The description does not add additional meaning beyond the schema; parameter purposes are clear from the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool polls a batch Judge run and lists the returned data (status, tally with sub-items, per-candidate verdicts), distinguishing it from related tools like eval_run_status or judge_run.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as judge_view, judge_try, or eval_run_status. The description explains what it does but not its appropriate usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description bears full burden. Discloses sync execution and no persistence, but omits side effects, authentication needs, rate limits, and return value. Insufficient for safe invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: two sentences, 15 words, no redundant information. Front-loaded with core action and key differentiator.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Describes core function but misses context for nested parameters (context, candidate) and output. No output schema; agent lacks guidance on return format. Adequate for simple usage but incomplete for full understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for top-level parameters. Description adds no extra meaning beyond schema descriptions. Nested fields (e.g., context.text) lack detail; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states verb 'evaluate', resource 'Judge against a single sample candidate', and context 'prompt/schema tuner'. Differentiates from siblings by noting 'Does not persist a run', which contrasts with judge_run.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies use case for quick testing/tuning without persistence. Lacks explicit alternative naming (e.g., 'use judge_run for full evaluation'), but the synchronous, single-sample nature provides clear context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must convey behavioral traits. It correctly indicates a read operation without side effects, but lacks details on authorization, rate limits, or error conditions. The description is accurate but minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that immediately states the purpose and key details. No extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description lists the expected return fields (provider, model, instructions, output schema, pass field), which sets proper expectations. It is comprehensive for a simple get operation, though missing mention of potential errors.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already fully describes both parameters with 100% coverage. The description adds no additional meaning beyond the schema, aligning with the baseline score of 3 for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies a clear action ('Get') and resource ('Judge's configuration'), listing specific fields included. It distinguishes from sibling tools like judge_list, which likely returns summaries, and judge_create/delete, which are mutations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like judge_list or judge_try. The purpose implies use for detailed configuration retrieval, but differentiation is left to the agent's inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only states 'Create a List' without disclosing behavioral traits such as idempotency, destructiveness, required permissions, or side effects. The description adds minimal behavioral context beyond the purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences and no wasted words. It front-loads the key action and defines the resource in a single sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (nested object, many parameters, no output schema), the description is too brief. It does not explain the return value, success/failure behavior, or error conditions. For a create operation, more context (e.g., response format, side effects) is expected.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description does not add any additional meaning beyond the schema; it simply restates the purpose. Parameters are well-documented in the schema, so no deduction.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a List' and defines a List as a collection of related Search Results. It is a specific verb+resource combination that distinguishes it from sibling tools like list_delete, list_edit, and list_get.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, conditions, or scenarios where other tools (e.g., list_edit for updating) are more appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must convey behavioral traits. 'Permanently delete' indicates irreversibility, which is key. However, it lacks details on side effects, authorization requirements, or what happens upon deletion.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words. It is appropriately sized for a simple delete operation and front-loads the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (2 required params, no output schema, no annotations), the description is insufficient. It does not explain what happens after deletion, any dependencies, or the return value, leaving gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents both parameters. The description adds no additional meaning or context beyond what 'listName' and 'accountName' imply in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Permanently delete a List.' clearly states the action (delete) and resource (List), with 'permanently' clarifying the scope. It distinguishes from sibling tools like list_create or list_edit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool vs. alternatives. The description does not mention prerequisites, caution about permanence, or situations where other tools might be more appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully convey behavioral traits. It merely states 'Edit List defaults and settings' without disclosing that it performs a partial update, whether it is destructive, what permissions are needed, or any side effects. The schema indicates optional parameters for updates, but this is not highlighted in the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no unnecessary words. It is appropriately concise, though it could benefit from additional details without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (nested object with 7 properties) and lack of output schema, the description is inadequate. It does not explain that the tool updates only provided fields (partial update), that it requires the list to exist, or what the return value is. More context is needed for a complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% description coverage for all parameters, so the description does not need to compensate heavily. The description adds no extra parameter meaning beyond what the schema already provides. A baseline score of 3 is appropriate as the schema carries the semantic load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Edit List defaults and settings' clearly states the verb (edit) and resource (list defaults and settings). It effectively distinguishes from sibling tools like list_create, list_delete, list_get, and list_restore_version, which serve different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies that the tool is used when one wants to modify list settings, but it provides no explicit guidance on when to use it versus alternatives or any prerequisites. As the only edit tool for lists, the use case is somewhat clear, but the lack of explicit directives limits the score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description bears full responsibility for behavioral disclosure. It merely says 'Retrieve the details' without indicating safety (read-only), error behavior (e.g., list not found), or any side effects. Minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with no irrelevant content. However, it could be more informative without sacrificing brevity, e.g., by specifying the type of details returned.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple retrieval tool with two well-named parameters, the description is minimally adequate. But lacking an output schema, it fails to clarify what 'details' are returned, leaving ambiguity. More context would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents the two parameters. The description adds no additional meaning beyond what the schema provides ('Name of the List', 'Name of the Account'), meeting the baseline but not exceeding it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Retrieve') and the resource ('a List'), making the basic purpose obvious. However, it does not differentiate from sibling tools like list_edit or account_get, and 'details' is vague without an output schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, scenarios, or exclusions. The agent must infer usage from the name and schema alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, description carries full burden. It discloses schema-only scope and roll-forward action, implying overwrite of current schema. However, it does not mention irreversibility, permissions, or impact on existing versions, leaving gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences provide core purpose succinctly without fluff. Slightly front-loaded; could benefit from additional critical details without becoming verbose, hence 4.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that modifies list state, description lacks details on side effects (e.g., version bump, loss of current schema), idempotency, and how to obtain version numbers. No output schema and no annotations amplify the need for more context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters are documented in the schema (100% coverage). Description adds no extra meaning to parameters, such as how to find the version number or format expectations, so baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool restores a historical schema version as the new latest version for a List, specifying it is a roll-forward and only affects schema, not search result data. This distinguishes it from sibling tools like group_restore_version.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives (e.g., group_restore_version). The phrase 'roll-forward, not rewind' hints at behavior but does not set selection criteria or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description solely states 'permanently delete,' which implies destructive behavior but provides no further context on authorization, reversibility, rate limits, or side effects. This is minimal transparency for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is concise and front-loaded. Every word is necessary and nothing is superfluous.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity, the description is adequate but minimal. It lacks context on error conditions (e.g., nonexistent item) and permission requirements. With an output schema absent, the agent has no indication of the return value. It is acceptable but not thorough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter already has a clear description. The tool description does not add any additional meaning beyond what the schema provides, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Permanently delete a media item from a media store.' It includes the verb 'delete' and specifies the resource, distinguishing it from sibling delete tools by resource type. However, it could be more specific about what constitutes a 'media item' or 'media store'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, nor any prerequisites (e.g., required permissions, existence of store/item). The agent must infer usage solely from the tool name and description, which is insufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.