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

No annotations are provided, so the description carries full burden for behavioral traits. The description clearly explains the meaning and purpose of each parameter like conflicts_with ('record conflicts rather than resolving them away') and kind ('epistemic status'). However, it does not disclose what happens on success (e.g., whether the value is persisted, if it returns the created record, or any side effects beyond recording). It also lacks details on idempotency, authorization, or constraints like uniqueness.

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 comprehensive but verbose, mixing parameter documentation with design philosophy. It front-loads the purpose clearly ('Record a held value belief'), but then devotes substantial space to inline parameter definitions that could be structured. For a tool with 10 parameters, the length is justified, but it sacrifices conciseness for completeness. Every sentence adds value, but the format feels monolithic.

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 high parameter count (10), 0% schema coverage, and the presence of an output schema (which reduces the need to describe return values), the description covers the tool's purpose and all parameter semantics thoroughly. The missing elements include typical success behavior (does it return the created value?) and any system-level side effects. The description is nearly complete for an agent to invoke it correctly, but could still benefit from concise success/return info.

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 0%, so the description must compensate fully. It does an excellent job by explaining each parameter's semantics: for 'source', it lists specific values (training, relationship, etc.) with meanings; for 'kind', it distinguishes between 'observed' and 'endorsed'; for 'scope', it clarifies who can query/challenge; and for 'conflicts_with', it explains the design rationale. The only gap is that this information is buried in the prose rather than structured.

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 records a held value belief, specifying the verb 'record' and resource 'value belief'. It distinguishes itself from siblings like value_read, value_list, and value_update by focusing on creation. However, the description does not explicitly contrast with value_drop (delete) or value_retract, which are complementary 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 provides implied guidance by detailing all parameters and their purposes, which helps the agent understand when to use this tool (to record a value). It does not explicitly state when not to use it or name alternatives, but the sibling context (value_read, value_list, etc.) indirectly suggests alternatives. A clear 'use this to create, use value_update to modify' would improve 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?

The description discloses the key behavioral detail that conflict relationships are bidirectional, which is not obvious from the name or schema alone. No annotations are provided, so the description carries the full burden. It does not mention performance, authorization needs, or what happens if the value has no conflicts, but for a single-param read operation with no annotations, the disclosed bidirectionality is sufficient 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 long and front-loads the core functionality in the first sentence. Every word is purposeful, and no redundant or filler content exists. The second sentence adds essential clarifying detail (bidirectionality). It could be more concise by merging the two sentences, but the clarity gained warrants the length.

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 single required parameter, a clear purpose, and no annotations or output schema details needed (the output schema exists but description needn't explain it), the description is sufficiently complete. It covers what the tool does, how the parameter works, and a key behavioral trait. A minor gap is the omission of what happens when no conflicts exist (empty list implied) or whether the tool requires an existing value.

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 0%, meaning the description adds all meaning for the parameter. It explains that value_id is a value whose conflicts will be returned, adding context that the schema alone lacks (schema only provides type string). This is adequate but not exceptional – baseline 3 is appropriate since the description does not specify the format or constraints of value_id (e.g., ID vs name, required prefix).

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 'Return' and the resource 'all values in tension with a given value.' It explicitly distinguishes its scope from sibling tools like value_read (which would presumably read a single value) and value_list (which lists all values), by focusing on the specific conflict relationship and bidirectional nature.

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 when to use this tool: when you need to find conflicting/conflicted relationships for a given value. It does not explicitly state when not to use it or name alternatives, but the sibling context (value_read, value_list) provides indirect differentiation. A small gap is the lack of guidance on prerequisites (e.g., value must exist).

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 states the operation is 'Permanent' and 'Irreversible', disclosing the key behavioral trait of destruction. However, it does not cover error handling (e.g., behavior if value_id does not exist) or any side effects, leaving minor 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?

The description consists of two terse, front-loaded sentences: the first declares the action and its irreversibility, the second offers an alternative. Every word is necessary and no redundancy exists.

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 (single parameter, output schema present), the description covers essential aspects: what the tool does, its irreversible nature, and when to use an alternative. The only notable omission is parameter description, but the tool's domain may make 'value_id' self-explanatory. Overall, complete enough for an informed selection.

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 0% and the description adds no meaning beyond the parameter name 'value_id'. The agent receives no elaboration on what the value_id represents or how to obtain it, failing to compensate for the lack of schema-level 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 'Permanently delete a value', using a specific verb ('delete') and resource ('value'). It also distinguishes from the sibling tool value_retract by mentioning it as an alternative, making its purpose unmistakable.

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 advises to 'Consider value_retract if you want to preserve the record of what was held', providing clear when-to-use and when-not-to-use guidance, and naming an alternative 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?

With no annotations provided, the description carries the full burden. It discloses filtering behavior and sorting order ('newest-first'), but omits details such as result limits, pagination, idempotency, or side effects. The behavioral context is adequate for a simple read operation 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 extremely concise: two sentences followed by a clearly formatted parameter list. Every sentence serves a purpose, and the structure is front-loaded with the tool's purpose. 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?

The description covers all parameters and sorting order. Given the presence of an output schema, return values need not be detailed. However, it does not mention potential result limits or pagination, which are common for list operations. Overall, it is nearly complete for a filtered list 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 input schema has 0% description coverage, so the description fully compensates by explaining each parameter's meaning and allowed values (e.g., status options, source types, scope values, tag requirements, carried_by semantics). This adds significant value beyond the bare 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 'List values, optionally filtered,' which is a specific verb and resource. It distinguishes from siblings like value_read (single value retrieval) and value_add (creation), making it evident that this is for listing multiple values.

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 explicit guidance on when to use this tool versus its siblings. While it describes the filters, it lacks statements like 'use this to get all matching values' or 'use value_read for a single value,' leaving the agent to infer 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 provided, the description carries the full burden of behavioral disclosure. It states the tool is read-only (implied by 'Read'), which is helpful, but doesn't disclose if this operation might trigger side effects (unlikely given the name, but not stated). The null return behavior is transparent, but details like latency, permissions, or rate limits are absent. The description is adequate but not thorough for a read 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 extremely concise: two sentences that cover purpose and a key behavioral detail (null return). There is no fluff or redundant 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?

Given the tool's simplicity (one parameter, no annotations, output schema exists but description needn't explain returns), the description is nearly complete. It explains what the tool does and the null behavior. However, with an output schema present, the description could optionally hint at the structure of the returned value, but this is not required. It slightly lacks context on when to use this versus other sibling 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?

The schema description coverage is 0%, meaning neither the schema nor description provides additional details beyond the parameter name 'value_id'. However, with only one parameter and a clear tool purpose ('Read a single value by ID'), the semantics are inherently clear. The description adds meaning by explaining that providing an ID returns the value or null. Given the simplicity, this is well-addressed.

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 'Read a single value by ID', which is a specific verb ('Read') and resource ('single value'). It also mentions the return behavior ('Returns null if not found'), which distinguishes it from siblings like value_list (which returns multiple) or value_add (which creates). However, it could further clarify that this is a lookup operation versus value_list's listing operation.

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 explicit guidance on when to use this tool versus siblings. For example, it doesn't indicate that this should be used when you have a specific ID and need only that value, whereas value_list might be for browsing. There are no alternatives or exclusions 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 provided, the description carries the full burden of behavioral disclosure. It clearly states that this is a non-destructive operation ('this is not a delete') and explains what happens: the retraction timestamp and reason are recorded, and history is preserved. This gives the agent confidence in the tool's 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?

The description is three sentences long, with the key action in the first sentence and the history preservation and sibling differentiation in the second and third. It is front-loaded and every sentence adds value. One point deducted for minor redundancy: 'the history of what was held and when is preserved' is slightly verbose but still useful.

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 (2 params, 1 required, simple types, output schema present), the description covers all essential aspects: purpose, side effects, non-destructive nature, and relationship to siblings. The output schema can explain the return format, so the description's lack of return value detail is acceptable. The tool is fully described 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?

Schema description coverage is 0%, so the description must compensate for parameter meaning. It does so effectively for the context: 'cause' is implied by 'retract a value with cause' (optional reason for retraction) and 'value_id' is implied as the target. While not a detailed parameter listing, the functional description is sufficient for an agent to infer usage. One point deducted for not explicitly naming both parameters in context.

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 ('Retract a value with cause'), the resource ('value'), and the effect ('Records the retraction timestamp and reason'). It also distinguishes itself from siblings by noting it preserves history and is not a delete, and explicitly names the alternative 'value_drop' for permanent 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?

The description provides explicit guidance on when to use this tool ('to retract with cause') and when not to ('use value_drop for permanent deletion'), directly differentiating from a sibling tool. This helps an agent decide between value_retract and value_drop.

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 correctly states 'Only provided fields are changed,' which implies a partial, non-destructive update. However, it does not disclose how array fields (tags, witnesses, etc.) are handled—whether they are replaced wholesale or merged. It also omits side effects like permission requirements or error conditions, leaving notable behavioral gaps for a tool with 12 parameters.

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 exceptionally concise—two sentences, each earning its place. The first sentence states the core purpose, the second adds critical behavioral detail ('Only provided fields are changed'), and the third provides an explicit alternative. There is zero fluff or 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?

Given the complexity (12 parameters, no annotations, multiple siblings), the description covers the basic update semantics and one sibling, but fails to explain array field behavior, required fields beyond the schema, or the output structure (though an output schema exists). It is minimally adequate but not thorough for a tool with this many parameter choices.

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 0%, yet the description adds no parameter-level information beyond 'fields.' Although parameter names like 'body', 'kind', 'source', and 'status' are somewhat self-explanatory, the description does not elaborate on allowed values, formatting, or the specific intent of each field. For a tool with 12 parameters, this lack of semantic elaboration hinders correct invocation.

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 'Update' and resource 'a value's fields', with the specific behavioral detail 'Only provided fields are changed.' It also directly distinguishes from the sibling tool 'value_retract' by explicitly directing agents to prefer that tool for retraction, which eliminates 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?

The description provides clear context: use it when you want to modify specific fields on an existing value. It explicitly directs agents to 'prefer value_retract' for retracting with a cause, offering a concrete alternative. However, it does not address when not to use it relative to other siblings like value_add (for creation) or value_drop (for deletion), which would strengthen guidance.

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