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

No annotations provided, and the description only states the action without disclosing side effects, idempotency, or required permissions. For a creation tool, 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?

Single sentence is concise and front-loaded. However, it could be slightly expanded to include output or usage context without losing efficiency.

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 and zero parameters, the description should at least mention what the tool returns (e.g., automation ID). It lacks this, making it incomplete for an agent to understand the full behavior.

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?

Input schema has 0 parameters (coverage 100%). With no parameters, the description need not add param info; baseline is 4.

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 creates automations of specified types (webhook, email, Slack, HubSpot). It uses a specific verb and resource, and distinguishes from update/delete siblings.

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 automation_update or automation_test. No context on prerequisites or scenarios.

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 only says 'permanently delete', which implies destruction but lacks details on auth requirements, irreversibility, or side effects. It adds minimal 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?

The description is extremely concise with a single, front-loaded sentence. While it could be more informative, it wastes no 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 no parameters and no output schema, the description sufficiently explains what the tool does. It could mention more about implications (e.g., no undo), but 'permanently' partially covers that.

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 in the schema, so the description does not need to add parameter meaning. The baseline of 4 applies per the scoring rules.

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 'delete' and the resource 'automation', and it naturally distinguishes from siblings like automation_create, automation_list, etc.

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 given on when to use this tool versus alternatives like automation_update or automation_test. The description does not mention any 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?

With no annotations, the description carries the burden. It indicates a read operation returning status and metadata, but lacks details on potential errors, pagination, or any side effects. Adequate for a simple list.

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 unnecessary words, achieving its 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 no output schema, the description partially explains results ('status and metadata') but is vague about what specific metadata is included. Sibling tools exist but no guidance is provided.

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 schema coverage is 100%. The description adds no parameter info, but the baseline for zero parameters is 4, indicating no additional meaning needed.

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 lists automations on a perspective, including status and metadata, which distinguishes it from sibling automation tools (create, delete, update, test) that have different verbs.

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 use for viewing automations but offers no explicit guidance on when to use this tool over alternatives or any cautionary notes.

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 of disclosing behavioral traits. It mentions 'mock conversation', implying no real data is affected, but does not explicitly state that the operation is read-only or has no side effects. The description lacks details on what happens during the test (e.g., does it modify anything? Is it safe to run repeatedly?).

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 is front-loaded with the key action. Every word contributes to the meaning, with no unnecessary elaboration.

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 no parameters or output schema, the description is relatively complete, but it fails to mention that the automation must exist or how the mock conversation is provided. The lack of context about prerequisites or behavioral expectations (especially given no annotations) leaves some gaps, though the tool's simplicity mitigates this.

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 no parameters (empty object), so schema coverage is 100%. The baseline score is 4 per the rubric for zero-parameter tools. The description does not add parameter information, but none is needed given the absence of parameters.

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: running an end-to-end test of an automation against a mock conversation. It uses a specific verb ('run') and resource ('automation'), and distinguishes itself from sibling tools (create/delete/list/update) which manage automations rather than test them.

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. It does not specify prerequisites (e.g., whether the automation must exist) or scenarios where this tool is appropriate. The description simply states the action without contextualizing its role relative to other automation 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 are present, and the description does not disclose any behavioral traits such as required permissions, side effects, or whether the automation must exist. With no annotations, the description carries full burden but is too 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 sentence, which is concise but overly brief. It lacks structure and front-loading of 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 absence of annotations, output schema, and detailed parameters, the description is incomplete. It does not clarify what fields can be updated or how to specify them, leaving the agent with insufficient 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?

The input schema is an empty object (no parameters), yet the description mentions 'Update fields' without specifying what fields. This is misleading as the schema does not define any parameters. Schema coverage is 100% trivially, but the description adds no useful 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 'Update fields on an existing automation', which clearly identifies the verb and resource. It distinguishes from sibling tools like automation_create, automation_delete, automation_list, and automation_test, but does not explicitly differentiate them.

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 usage is only implied (update an existing automation), with no exclusions or context about prerequisites 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?

No annotations provided, so the description must disclose behavioral traits. It only lists actions without mentioning side effects, authentication, rate limits, or how the three actions are triggered. Lacks clarity on whether this is a single command or multiple.

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 single sentence is concise, but the structure is a bit ambiguous with three verbs. It could be more clearly separated. Still, 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?

With no parameters, no output schema, and no annotations, the description should provide more context about how to use the tool. It does not explain the workflow, prerequisites, or return values. Incomplete for a management 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?

Input schema has 0 parameters, so description cannot add parameter info. Per rules, baseline is 4 for 0 params. Description implies multiple actions but does not clarify how they are invoked, which is a minor gap.

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 manages integrations by listing providers, connecting them, and searching tools. It distinguishes itself from siblings since no other sibling tool handles integrations. However, the grouping of multiple actions in one sentence slightly reduces specificity.

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. Siblings do not include integration tools, so it is the sole tool for integrations, but there is no precondition or scenario described for its use.

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 '48-hour magic-link' implying expiry but does not disclose side effects, return value, or authentication needs. The optional email sending is vague.

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 of 11 words, front-loaded and efficient. Every word adds value, no repetition.

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 parameters, the description lacks detail on participant specification, email sending mechanism, and return output. Agent cannot fully infer tool behavior without further 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?

Input schema has 0 parameters with 100% coverage, so baseline is 3. Description adds meaning about the invite creation and optional email, but does not clarify how participants are identified or how email sending is controlled.

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 'Create', resource 'magic-link invites for participants', and attributes '48-hour' and 'optionally sent via email'. It is specific and distinguishable from sibling tools.

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 any prerequisites. The description does not provide context for appropriate usage scenarios.

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 all burden. It mentions 'long-poll' but does not explain behavior like blocking, timeout, error handling, or what triggers completion. The agent lacks critical operational details.

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 superfluous words. It is maximally concise for the information provided.

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 zero parameters and no output schema, the description is still incomplete. It fails to explain what 'long-poll' means concretely, what happens on completion, or how to handle failures. The tool might be simple, but the description should still cover expected behavior.

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 description coverage is not an issue. However, the description does not clarify how the tool identifies which job to poll, which is a semantic gap. A baseline of 4 is adjusted down due to missing contextual linkage.

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 the verb 'Long-poll' and the resource 'perspective design job', indicating the action is to wait for a job to complete. It is clear and distinct from sibling tools like perspective_create or perspective_get, though the exact scope of 'design job' could be more precise.

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 (e.g., having a job ID) or context that would help an agent choose this over other perspective 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; description only says 'create', implying mutation but does not specify side effects, auth needs, or what gets created. Fails to compensate for missing 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?

Single sentence, no wasted words. Perfectly 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?

Lacks explanation of what a 'perspective' is or what 'natural-language brief' entails. No output schema means description should clarify return value; it does not.

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?

Input schema has 0 parameters and 100% coverage; description adds no parameter details but is not required to. Baseline score of 4 applies as per guidelines for 0 params.

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 states a clear verb+resource: 'Create a new perspective from a natural-language brief'. It is specific but does not differentiate from sibling tools like perspective_update or automation_create.

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., perspective_update, automation_create). No exclusions or 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the purpose and does not mention side effects, permissions, rate limits, or safety. Although 'get' implies read-only, the description should explicitly note behavioral traits like read-only hint.

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 of 9 words. It is front-loaded with the verb 'Get', immediately stating the action. Every word is necessary; there is no redundancy or fluff. Perfectly sized for a tool with no parameters.

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 zero parameters, no output schema, and low complexity, the description is complete. It explains what the tool returns ('full configuration and stats'), which is sufficient for an agent to understand its purpose and use it 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?

The input schema has no parameters (schema coverage 100%), so there is nothing to add beyond the schema. With zero parameters, the description is not required to explain param semantics. The baseline of 4 is appropriate as it does not need to compensate for missing info.

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 'Get full configuration and stats for a perspective' clearly specifies the action (Get), resource (perspective), and scope (full configuration and stats). This distinguishes it from sibling tools like perspective_get_stats (stats only) and perspective_get_conversations (conversations only).

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: use this tool when needing the complete configuration and stats of a perspective. While it does not explicitly mention when not to use it or list alternatives, the purpose alone provides clear decision guidance, especially given the sibling tools' distinct purposes.

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 bears full responsibility for behavioral disclosure. It only states the output content but does not reveal if the operation is read-only, requires authentication, or has any side effects.

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 sentence of 10 words conveys the essential purpose. Every word is meaningful with 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?

With no output schema, the description partially covers return values by naming 'conversation details, transcript, trust assessment'. However, it lacks details on structure, pagination, or error conditions, which are relevant for a retrieval 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 tool has zero parameters, and schema coverage is 100%. The description does not add parameter details, but none are needed. Baseline for 0 params is 4.

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 retrieves full conversation details, specifying 'transcript' and 'trust assessment' as included content. It uses the verb 'Get' with a specific resource 'conversation', distinguishing it from sibling tools like 'perspective_get' or 'perspective_get_conversations'.

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 'perspective_get_conversations' for listing or 'perspective_get' for single perspective details. No mention of prerequisites or 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. Only mentions 'token-efficient' without explaining what that entails (e.g., minimal data, pagination, rate limits). Does not clarify read-only nature or return format.

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 action and purpose, no 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 no parameters, no output schema, and many sibling tools, the description is too vague. It does not explain what 'batch fetch' returns (full conversations, summaries, etc.) or how it differs from listing tools.

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?

Input schema has zero parameters, so description need not add param info. Baseline 4 per rules for 0-param tools.

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 'fetch' and resource 'conversations', and adds qualifiers 'batch' and 'token-efficient'. However, it does not distinguish from sibling tools like 'perspective_list_conversations' or 'perspective_get_conversation'.

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 'perspective_get_conversation' or 'perspective_list_conversations'. Lacks any when-to-use or when-not-to-use 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?

Describes a non-destructive retrieval operation, listing what is returned, but lacks disclosure of permissions, rate limits, or response format. Without annotations, the description carries full burden and is minimally transparent.

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 the action and key details, 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 zero-parameter retrieval tool, the description conveys the main output (embed snippets list and SDK reference). However, it lacks detail on the format of the snippets or SDK reference, which could be important for an 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?

No parameters exist (schema coverage 100%), and the description adds value by enumerating the embed snippet types, providing context 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?

Describes a specific verb 'Get' and resource 'embed snippets' with a list of types (fullpage, widget, popup, slider, float, card) and 'SDK reference', clearly distinguishing from sibling tools that create, update, or list perspectives.

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 retrieving embed options, but does not explicitly state when to use this tool over alternatives or provide any exclusions or preconditions.

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 full burden for behavioral details. It states the tool returns a URL but does not disclose whether the URL is temporary, if side effects occur, authentication requirements, or rate limits. The transparency is basic.

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 filler. Every word adds value: 'Get', 'shareable preview URL', 'for testing before deployment'. It is appropriately sized 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?

Given the tool's simplicity (no parameters, no output schema), the description is fully complete for an agent to understand its purpose and usage. No additional context 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?

The tool has no parameters (input schema is empty), and schema coverage is 100%. According to the guidelines, 0 parameters yields a baseline of 4. The description does not need to add parameter information.

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 resource 'shareable preview URL' with a specific context 'for testing before deployment'. This distinguishes it from sibling perspective_* tools like perspective_get or perspective_create, which focus on other operations.

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 'for testing before deployment' implicitly suggests when to use the tool, but it lacks explicit guidance on when not to use it or alternatives (e.g., perspective_get for retrieving the actual resource). No exclusions or comparisons to siblings 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?

The description offers minimal behavioral insight. It does not indicate that the tool is read-only, what side effects occur, or any special requirements (e.g., authentication, rate limits). With no annotations, the description carries full burden but fails to disclose key traits.

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, but it lacks necessary details. It is not tautological, yet it fails to earn its place by omitting critical information about what statistics are aggregated or how the time window is specified.

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 zero parameters, no output schema, and no annotations, the description should compensate by clarifying the tool's semantics. It does not explain what 'stats and distributions' refers to, nor how the time window is defined. The tool is incomplete for an agent to use without further 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?

The input schema has no parameters, but the description mentions 'over a time window', implying a temporal parameter exists. This contradiction causes confusion. Baseline for 0 parameters is 4, but the misleading implication lowers 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 'Aggregate stats and distributions over a time window' clearly indicates the tool's function of providing aggregated statistics over a temporal range. While it does not explicitly name the resource ('perspective'), the tool name and sibling tools strongly imply it pertains to perspectives. It distinguishes from siblings like perspective_get (single item fetch) and perspective_list (list items).

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 any prerequisites, context, or exclusions, leaving the agent to infer usage without 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states 'list' and 'search' without any details on pagination, ordering, limits, or whether search is exact/fuzzy. This is insufficient for an agent to predict tool behavior.

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. Every word is informative, and it efficiently conveys the dual functionality.

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 and no output schema, the description is somewhat complete but lacks context on how the workspace is determined (e.g., from authentication or context), and does not mention any default behavior or error states.

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 the baseline score is 4. The description does not need to add parameter meaning since there are none. It correctly implies no arguments are needed.

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 lists perspectives in a workspace or searches by name across workspaces. It distinguishes from sibling tools like perspective_get (single) or perspective_list_conversations (different resource). However, it lacks specificity on the output or behavior of listing.

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 two usage modes (list vs search) but does not explicitly guide when to use this tool over alternatives like perspective_get or perspective_list_conversations. No exclusions 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?

The description claims filtering capabilities (by status, trust score, date) but the input schema has zero parameters, creating a contradiction. No annotations are present to disclose any behavioral traits.

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, brief sentence, which is concise. However, the lack of detail about the filters makes it somewhat incomplete for a tool with no parameters.

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 implied filtering capability (status, trust score, date) and the absence of both input parameters and output schema, the description fails to explain how to use the tool 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?

Since there are no input parameters, schema coverage is 100%, but the description mentions filters that cannot be specified via the schema. This misleads rather than adds meaning beyond 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 states 'List conversations with filters by status, trust score, and date', which is a clear verb+resource combination. However, it does not differentiate from sibling tools like 'perspective_get_conversations' or 'perspective_list', and the mention of filters is inconsistent with the empty input 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 compared to alternatives such as 'perspective_get_conversations' or 'perspective_list'. The description lacks explicit context for 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?

No annotations are provided, and the description does not disclose whether this tool modifies state, requires authentication, or has side effects. The agent has no behavioral expectations.

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, no wasted words. However, it could be slightly more informative without losing conciseness, 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?

Given the simplicity (0 params, no output schema), the description fails to provide context like prerequisites (e.g., after perspective_create) or what triggers a follow-up question. An agent may not know when to invoke 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?

Input schema has no parameters, so schema coverage is 100%. The description need not add parameter details, and the baseline of 4 is appropriate as there is no missing information.

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 answers follow-up questions during perspective design, distinguishing it from creation, retrieval, and update tools. However, 'answer a follow-up question' is somewhat vague about what that entails.

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 perspective_update or perspective_await_job. The description does not provide context for selecting this tool.

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 is only 5 words and fails to disclose any behavioral details such as whether it adds to or replaces existing data, authentication needs, or side effects (e.g., mutating state).

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 with no wasted words, but it is too terse to be truly helpful. Front-loading is present but at the cost of essential detail.

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 zero parameters in schema, no output schema, and no annotations, the description provides almost no context. It fails to explain the required input format, the effect of the action, or the expected output.

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 is an empty object type with no properties. The description only mentions 'natural-language feedback' but does not specify what fields the object should contain (e.g., id, feedback), leaving the agent entirely guessing.

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 'refine a perspective' which clearly indicates modifying an existing perspective, distinguishing it from create, get, list, etc. However, it does not specify how to identify which perspective to refine, leaving ambiguity.

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 perspective_create or perspective_get. The agent must infer usage context without explicit when-to or when-not-to instructions.

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 burden. It only states 'get details', implying a read operation, but fails to clarify whether it requires authentication, returns a summary or full details, or if it operates on the current workspace context. Minimal behavioral disclosure.

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, short sentence makes it concise and easy to parse. However, it could be slightly more informative without sacrificing conciseness (e.g., specifying which workspace). Still, it earns a 4 for being appropriately sized.

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 is provided, so the description should hint at what 'details' are returned, but it does not. Additionally, no annotations give context. For a tool with no parameters, the description is incomplete regarding return values and 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?

The tool has zero parameters, and the schema coverage is 100%. According to the rubric, when there are 0 params, the baseline is 4. The description does not add parameter information, which is acceptable given no parameters exist.

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 verb 'Get' and resource 'workspace', indicating a retrieval operation. However, it does not differentiate from the sibling tool 'workspace_get_default', which likely retrieves the default workspace specifically. A score of 4 reflects clarity but lack of sibling distinction.

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 like 'workspace_get_default' or 'workspace_list'. The agent is left to infer usage context without explicit instructions.

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 only states 'Get', implying a harmless read operation, but offers no details about return format, authentication, or side effects. Minimal 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?

A single, efficient sentence with no wasted words. However, it could be slightly 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?

For a parameterless, read-only tool with no output schema, the description is minimally adequate. It doesn't explain what constitutes the 'default' workspace or what the response contains, which could be clarified.

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 (type: object, no properties), so schema coverage is 100%. Per guidelines, 0 parameters yields a baseline of 4. The description adds no param info, but none is needed.

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 'Get your default workspace' clearly states the action and resource. It differentiates from sibling tools like 'workspace_get' (which likely requires a workspace ID) and 'workspace_list' (which returns all workspaces). However, it does not explicitly distinguish itself.

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 prerequisites, when not to use it, or related 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, so the description must carry full burden. It describes a simple read operation but does not disclose any behavioral traits like pagination, rate limits, or response 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?

Single sentence, no wasted words, and front-loaded with the key action.

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 (no params, no output schema), the description is largely complete. However, it could mention if the list is paginated or ordered.

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?

Input schema has 0 parameters with 100% coverage, so the description adds no parameter info beyond the schema. 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?

The description clearly states the verb 'List' and the resource 'workspaces you can access', distinguishing it from sibling tools like workspace_get and workspace_get_default.

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?

While no explicit when-to-use or alternatives are given, the context from sibling tool names implies that this is the go-to for listing all workspaces, whereas others are for specific retrieval or operations.

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