concordance

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

With no annotations provided, the description fully carries the burden of behavioral transparency. It discloses key traits: deterministic extraction, conservative design (only unambiguous patterns), no guessing, no implied full coverage, and that it returns per-claim details (source quote, verdict, trail) and a claim count.

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 paragraph with clear front-loading of the verb 'Audit'. It is detailed but efficient, with no redundant sentences. It could be slightly more concise, but each sentence contributes useful 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 tool's complexity (auditing quantitative claims) and lack of output schema, the description adequately explains the return value (sealed report with per-claim details). It covers extraction rules, verification, and output format. It could mention edge cases (e.g., no claims found) but 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%, so the schema already describes both parameters. The description adds minor value by noting the 'seal' parameter's default value (true) and its purpose (mint a re-checkable seal) but does not enhance the 'text' parameter beyond the schema. 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 tool audits whole texts extracting and verifying quantitative claims, returning a sealed coverage report. It identifies the resource (text) and the action (audit), and is specific about the types of claims. However, it does not explicitly distinguish itself from sibling tools like 'verify' or 'seal_fetch', which could be confused.

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., 'verify' for simpler checks, 'seal_fetch' for retrieving seals). The description implies its use for auditing quantitative claims but does not specify when it is appropriate or when other tools should be used instead.

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 important behavioral traits: badge is re-checkable, states exact N, never a competency claim. However, missing details on permissions, side effects, or what happens if seals are invalid.

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?

Concise two-sentence description that front-loads the main action. Second sentence is slightly cryptic but adds nuance without excess 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?

Incomplete for a 4-parameter tool with no output schema and no annotations. Description covers purpose but not parameter semantics or return value format.

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 parameter descriptions in schema (0% coverage) and description does not explain any parameter meanings. For 4 parameters including `seal_hashes` and `private_key`, this is a critical 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 issues a badge over sealed checks, specifying it is a receipt pointing at N seals that still stand. It distinguishes from sibling 'badges_verify' by focusing on issuance rather than verification.

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 usage context (over already-sealed checks) but lacks explicit when-to-use or when-not-to-use compared to siblings like 'badges_verify'. No guidelines on 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 description carries full burden. It discloses that the tool recomputes the seal count ('N recomputed, not trusted'), indicating it does not trust cached values. This is a key behavioral trait. It does not mention side effects, authentication, or rate limits, but the operation appears read-only and lightweight.

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 fluff, front-loaded with the action. Every word adds value. Ideal length for the information conveyed.

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?

Tool is simple (1 param, no nested objects, no output schema). Description covers core function and return value. Missing parameter explanation and potential prerequisites (e.g., badge must exist), but overall completeness is good for this complexity level.

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 0% (parameter 'hash' not described in description). The description mentions 'badge' and 'seals' which imply hash is the badge identifier, but does not explicitly define the parameter format or domain. With only one required parameter, the description should clarify its purpose and 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?

Clear verb-resource pair: 'Re-check a badge' and 're-verifies every seal'. Distinguishes from siblings by specifying recomputation of seal counts and returning a recomputed count, which is unique among sibling tools like 'verify' (likely a simpler check) and 'badges_issue'.

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?

Implied usage: use when you need to re-verify a badge's seals and get the current count. No explicit when-not or comparison to alternatives like 'audit' or 'verify'. Guidance is minimal but adequate for a narrow-purpose 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 are provided, so the description must disclose behavioral traits. It only states what is returned, but does not mention whether it is read-only, requires authentication, has rate limits, or any side effects. The retrieval nature is implied but not explicitly 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, concise sentence that efficiently conveys the core functionality. No unnecessary words, but lacks structure like bullet points or emphasized keywords.

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 input schema (one parameter) and no output schema, the description is reasonably complete for a basic retrieval tool. However, it falls short on behavioral details and usage guidance, which are needed for full contextual 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 sole parameter 'id' is described in the description as referring to 'one card', which adds context beyond the schema (which only defines type string). However, schema description coverage is 0%, and the description does not specify the expected format or source of the id.

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 returns cards related to a given card, distinguishing between 'explicit links' and 'same-shelf siblings'. It differentiates from siblings like 'card_get' (single card) and 'cards_browse' (general browse). However, it omits an explicit verb like 'retrieve' or '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?

No guidance on when to use this tool versus alternatives. The description does not mention any prerequisites, filters, or context for selecting this tool over siblings like 'cards_browse' or 'card_get'.

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 implies a read operation ('fetch') but does not disclose behavior such as error handling (e.g., what if id not found), auth requirements, rate limits, or side effects. The term 'the keeping' is undefined and ambiguous.

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 filler. It conveys the core purpose efficiently. Every word is necessary. Perfect 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 simple tool with one parameter and no output schema, the description is minimally complete. However, it lacks context on what 'the keeping' refers to, return format, and error conditions. The tool's simplicity does not excuse missing important contextual information that would help an agent 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?

Schema coverage is 0%, and the description adds no parameter details beyond the schema. However, the single parameter 'id' is self-explanatory as a record identifier. The description mentions 'by id' implicitly. A score of 3 is appropriate as the parameter is simple and the schema already defines it, though no extra value is added.

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 'one card (the full record)'. The context 'by id' is implied by the required parameter. While it does not explicitly differentiate from sibling tools, the tool name itself is unique among siblings. A score of 4 reflects clear purpose without explicit sibling differentiation.

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 cards_browse or other get tools. No when-not-to-use or context cues provided. The description only states what it does, not its 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 must fully disclose behavior. It mentions pagination and filtering but omits details like read-only nature, error conditions, or what happens with missing parameters. The term 'card briefs' is undefined, leaving uncertainty about return content.

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 it omits important details that could be added without increasing length significantly. It front-loads the purpose but lacks structured breakdown of parameters or usage notes.

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 browse tool with no output schema, no annotations, and 3 undocumented parameters, the description is too terse. It fails to explain return structure, pagination limits, or relationship to sibling tools like 'search'. The context is insufficient for an agent to 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?

Schema coverage is 0%, so the description should explain all parameters. It only mentions 'optional shelf filter' for the shelf parameter, and 'paginated' implies limit/offset, but gives no specifics on types, defaults, or valid values. This is insufficient for proper tool 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 action 'browse', the resource 'the keeping' (though domain-specific), and key features: pagination, optional shelf filter, and returning card briefs. It distinguishes from siblings like 'card_get' (single card) and 'cards_stats' (statistics), but the term 'keeping' is ambiguous.

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 gives no guidance on when to use this tool over alternatives such as 'search', 'card_get', or 'cards_stats'. It merely states pagination and shelf filter without context on when to choose this browsing interface versus others.

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 only states what counts are produced, with no mention of side effects, safety, or whether it is read-only. This is insufficient for a tool with zero annotation coverage.

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 terse sentence, which is concise but lacks structure and fails to provide sufficient context. It is front-loaded but still under-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 the simplicity (no parameters, no output schema), the description should clearly define the return values and domain context. However, 'keeping' is unexplained, and the format of counts is unspecified, making it incomplete for an agent to reliably use the 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, so the input schema covers all cases. Per guidelines, '0 params = baseline 4'. The description adds no parameter semantics beyond the schema, which is acceptable.

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 'Counts over the keeping — total, by shelf, by surface' indicates counting but uses an ambiguous term 'keeping' that may be domain-specific. It does not clearly specify what resource is being counted, nor does it distinguish from sibling tools like cards_browse.

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. There is no mention of context, prerequisites, or exclusions, leaving the agent to infer usage from the vague description.

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 carries full burden. It only discloses one negative constraint (no grading) but does not describe what the tool actually does, its side effects, or return value.

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 it is under-informative and does not earn its place by adding necessary clarity.

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 output schema and the abundance of sibling coaching tools, the description is incomplete. It does not specify what the tool returns or when an agent should invoke it.

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%. The description adds no parameter meaning beyond the schema, which is trivially empty. A baseline of 4 is reduced because the description fails to provide any context about the tool's function.

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 vaguely states the tool is about coaching and explicitly says it does not grade, but fails to specify any action or resource. Among many sibling coaching tools, it does not differentiate its purpose.

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 coach_mastery or coach_overview. Only a boundary (never grades) is 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 must fully disclose behavior. It indicates the tool returns a seal but does not clarify whether it is read-only, modifies state, requires authentication, or has side effects. The metaphor 'seal' and 're-checkable' hint at immutability but are 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?

The description is very short (two sentences) and front-loaded with the core action. However, the use of poetic language ('HONEST', 'receipt for progress, never a grade') sacrifices clarity for style. It earns its place but could be more direct without losing meaning.

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 output schema and annotations, the description should provide more context about the return value ('seal') and the parameter format. The agent is left with insufficient information to correctly invoke the tool, especially regarding what 'completed' is expected to be (array of what?). Sibling tools like seal_fetch exist but no relationship is explained.

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 a single parameter 'completed' of type array with 0% description coverage. The description says 'INTEGER count', suggesting a number, but the parameter is an array. This inconsistency adds confusion rather than clarity. The description fails to explain what the array should contain or how to format the data, leaving the agent to guess.

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: 'seal an HONEST INTEGER count of completed units' and returns a re-checkable seal. The verb 'seal' and noun 'count' specify the action and resource, and it distinguishes from sibling tools like coach_guidance or coach_overview which focus on guidance or overview rather than recording progress.

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 recording completed units but does not explicitly state when to use this tool versus alternatives like badges_issue or seal_fetch. No when-not or exclusion criteria are provided, leaving the agent to infer context. The mention of 'receipt for progress, never a grade' hints at appropriate scenarios but lacks explicit 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?

No annotations provided, so description carries full burden. Only mentions determinism; no disclosure of side effects, permissions, rate limits, error handling, or authentication needs.

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 front-loaded 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?

Covers purpose and parameter usage, but lacks output description, error handling, authentication, or prerequisites. Without output schema or annotations, additional 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 0%, but description explains both parameters: 'after' as unit id for next lesson, 'subject' for path selection, adding meaning beyond empty schema 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?

Clearly states it returns the next lesson in a subject deterministically, with specific verb 'coach_next' and resource 'lesson'. Distinguishes from sibling tools like coach_recommend (likely non-deterministic) and coach_unit (specific unit).

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?

Provides explicit guidance on when to omit or pass the 'after' parameter (first unit vs. following one), but does not mention when not to use this tool vs. alternatives like coach_recommend or coach_unit.

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?

Adds behavior note 'Verbatim; never generated' indicating read-only retrieval, but lacks details on safety, auth, or error behavior. No annotations provided to supplement.

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. First sentence defines purpose and content; second covers parameter usage and a key behavioral constraint.

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 input parameter with default, output components, and a behavioral note. Missing explicit list of valid subject values, but sufficient for a simple retrieval tool given 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?

Adds meaning to the sole parameter 'subject' by explaining it selects the path and defaults to 'read'. Compensates for 0% schema description 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?

Clearly states it returns a subject's path overview with unit count, tracks, and briefs. However, it does not explicitly differentiate from sibling tools like coach_subjects or coach_unit.

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?

Provides parameter usage hint with default value 'read', but no guidance on when to use this tool versus 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?

No annotations are provided, so the description carries the full burden. It states the tool is adaptive and returns a lesson (found, not generated), implying it is a read operation. However, it does not explicitly clarify that it is non-destructive or mention any required permissions or side effects, leaving some ambiguity.

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—one core functional statement and one clarifying tagline—with no extraneous words. It is front-loaded with the essential purpose and remains highly 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 tool has only two parameters, no annotations, and no output schema, the description provides enough context for basic use (inputs and behavior). It lacks details on output format or error cases, but for a simple recommendation tool, 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?

The input schema has two parameters with 0% description coverage, but the tool description explains 'completed' as 'given completed unit ids' and implies 'subject' from context. This adds significant meaning beyond the raw schema, compensating 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 the verb ('recommend'), resource ('next lesson'), and context (based on completed unit ids and prerequisites). It distinguishes from siblings by emphasizing adaptiveness and that it finds existing content, not generates. The phrase 'Found, never generated' adds 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?

The description implies when to use the tool: when a student has completed units and needs the next lesson meeting prerequisites. It does not explicitly state when not to use it or compare to similar siblings like 'coach_next' or 'coach_guidance', but the usage context is clear.

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 states the tool returns subjects with unit counts and hints at 'read' being a key entry point, but does not mention whether the call is read-only, requires authentication, or any side effects. The behavioral details are 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 with a parenthetical list, making it concise and front-loaded. However, it lacks structural elements like bullet points or sections that could improve readability.

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 return data (subjects and unit counts) but does not specify the exact format or structure (e.g., object/array). The hint about 'read' being the door in adds some context, but more detail on the return value and typical usage 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?

The input schema has zero parameters, so the description's job is minimal. The baseline is 4, and the description adds no parameter information beyond the schema, which is acceptable.

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 that the tool lists subjects a learner can study, with examples like 'read / mcguffey / aesop', and indicates each comes with a unit count. It is distinct from sibling coach tools (e.g., coach_guidance, coach_next) which focus on other aspects.

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 this tool is for viewing available subjects, and notes that 'read' is the starting point, but does not explicitly state when to use this tool versus other coach tools (e.g., coach_overview, coach_recommend). Usage context is implied rather than stated.

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 output is 'VERBATIM as authored', implying no transformation, but does not confirm read-only nature, authentication requirements, side effects, or error conditions. The single sentence offers 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 concise (one sentence) but lacks structure. It is front-loaded with a dash separator, but the information is minimal. A bit more detail could be provided without harming 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 the absence of output schema and low parameter documentation, the description is insufficient for an agent to reliably invoke the tool. It does not explain the relationship between the input parameters and the returned content, nor how to handle 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?

Schema description coverage is 0%, so the description must explain parameters. It does not mention 'id' or 'subject' whatsoever. The description only describes the output, leaving the agent unsure how to provide correct inputs.

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 resource ('Coach — one unit') and indicates it returns the verbatim content including rule, examples, decodable sentence, and checks. This clearly distinguishes it from sibling tools like coach_mastery or coach_next. However, it lacks an explicit verb (e.g., 'Get' or 'Retrieve'), which slightly reduces clarity.

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 coach_mastery or coach_next. The description does not mention any preconditions, context, or exclusions 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 provided, so description must carry full burden. The term 'deterministic' and 'same all day' suggest consistency, but no disclosure of side effects, permissions, or output characteristics. Minimal behavioral insight.

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 short—one sentence—but loses points for being uninformative. Conciseness is not valuable if it omits critical details. Could be improved with clear action and parameter explanation.

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 is simple (one param), but the description is incomplete: no mention of return value (no output schema), no explanation of 'seed', and no behavioral context. The agent would struggle to invoke this tool 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?

Input schema has one optional parameter 'seed' (string) with 0% description coverage. Description does not explain what 'seed' controls or how it affects the result. With no schema documentation, the description should compensate but fails entirely.

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 is vague: 'deterministic card of the day from the keeping' is unclear about what a 'card' is and what 'the keeping' means. It does not clearly state the action of retrieving or generating a card, making it hard for an agent to understand the tool's purpose. Siblings like 'card_get' and 'cards_browse' suggest different retrieval patterns, but no differentiation is provided.

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 'card_get' or 'cards_browse'. No context about prerequisites or exclusions. The description fails to inform the agent about 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?

No annotations are provided, so the description carries full burden. It declares the tool is 'read-only' and lists the data it returns, but does not disclose behaviors for invalid inputs or edge cases.

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 front-load the key purpose ('The map: a read-only view') and provide additional context without 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?

For a simple tool with one optional parameter and no output schema, the description adequately explains the output (scaffold members, depth, etc.) and the effect of omitting the parameter. It is sufficiently complete for its complexity.

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 0% schema description coverage, the description compensates by explaining that 'axis' is a string specifying one axis, and omitting it yields an overview of all axes. This adds significant meaning 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 it provides a 'read-only view of one axis' with specific contents like scaffold members and depth. It distinguishes itself by mentioning the optionality of the axis parameter for an overview of all axes, but does not explicitly differentiate from sibling tools like grid_dimension.

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 advises to omit 'axis' for an overview of all axes, offering some guidance on parameter usage. However, it lacks explicit instructions on when to prefer this tool over alternatives or any 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, and the description gives no behavioral information. It does not state whether the tool is read-only, has side effects, or requires authorization. The description is a static noun phrase with no 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?

The description is extremely brief (one phrase), but this conciseness sacrifices clarity and usability. It is not front-loaded with an action verb, and the structure does not help an agent understand usage.

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 schema (one param, no output schema) and no annotations, the tool is low complexity, but the description fails to cover even the basic purpose. It does not explain what the tool returns, how to use the parameter correctly, or any context about scaffold members.

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 0% description coverage for the single parameter 'dimension'. The description mentions 'scaffold member (dimension)' but provides no additional meaning about the parameter's format, allowed values, or how it relates to the scaffold member.

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 is a noun phrase lacking an action verb; it does not specify what the tool does (e.g., retrieve, list, get). It vaguely describes what the result is but not the operation. The sibling 'grid_axis' suggests possibly similar functionality, but no differentiation is made.

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 'grid_axis'. There is no mention of prerequisites, context, 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 provided; description discloses attribution, signing, and verbatim nature. But lacks details on permissions, side effects, or output. Adequate 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?

Single sentence, direct. Could be slightly more structured but 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 8 parameters and no output schema, the description is too brief to be complete. Lacks explanation of key fields like 'id', 'kind', 'refs', 'topics', and 'subject_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?

Schema description coverage is 0%, and the description does not explain any of the 8 parameters despite mentioning 'handle' and 'signing' implicitly. No parameter-level guidance.

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 adds a verse/note/question to a group study, with attribution and optional signing. It specifies verbatim content not engine-verified, but does not differentiate from sibling tools like study_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 vs alternatives. No mention of 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?

With no annotations provided, the description adds behavioral context: the group is pseudonymous and requires a handle, not personal info. It does not disclose permissions, side effects, or return behavior, 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?

The description is two sentences and front-loaded with the main action. The second sentence about the children's coach is somewhat unclear and could be more concise or combined.

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 creation tool with no output schema and no annotations, the description is insufficient. It omits what happens after creation (e.g., confirmation, errors) and does not cover parameters adequately.

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 5 parameters, none described in the text. Only 'topic' and 'handle' are indirectly hinted. With 0% schema description coverage, the description fails to explain parameter meaning or usage.

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 action ('Open a study group around a topic') and distinguishes it from siblings like group_join and groups_list. It specifies the resource (group) and the key constraint (pseudonymous, no personal info).

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 adults ('for grown believers') and mentions the children's coach as a separate surface, giving some context. However, it lacks explicit guidance on when to use this versus other group tools or what prerequisites 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?

Without annotations, the description carries full burden. It notes that member handles exclude ids/PII, but fails to disclose side effects, idempotency, or authentication needs. Partial transparency is provided but insufficient for a retrieval 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 fragment, which is concise but not structured as a complete sentence. It fails to front-load the action (retrieve), making it less 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?

Given one parameter, no output schema, and no annotations, the description is insufficient. It does not specify error handling, return format, or pagination, leaving significant gaps 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?

The sole parameter 'id' has no schema description (0% coverage) and the description does not clarify what it represents (e.g., group id, user id). No additional semantics are provided beyond the parameter 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 tool returns information about a study group: topic, member handles (no ids/PII), and shared-study cards. However, it lacks an explicit verb indicating retrieval (implied by name 'group_get') and does not differentiate from sibling tools like groups_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?

No guidance on when to use this tool versus alternatives such as groups_list (which lists groups). There is no mention of prerequisites (e.g., group existence, user membership) 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?

Discloses key behavioral traits: consent-based, pseudonymous, idempotent. However, lacks details on side effects (e.g., membership addition, notifications) given no annotations are 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?

Extremely concise single sentence, front-loaded with key behavioral attributes, 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 simplicity, the description fails to explain parameter semantics and usage context, making it incomplete for an agent to correctly invoke the 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 description coverage is 0% and the description provides no explanation of the three parameters (id, handle, subject_id). Their roles are entirely unclear.

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 'Join' and the resource 'study group', with additional context (consent-based, pseudonymous, idempotent) that distinguishes it from sibling tools like group_create 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 (e.g., group_create, group_get) or prerequisites (e.g., existence of group, user authorization). The description does not specify conditions for joining.

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 that members are handles only with no PII, which is key behavioral info. No annotations exist, so this fills the gap well, though it omits details like pagination or ordering.

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 with no wasted words, front-loaded purpose and filtering behavior.

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 one optional param and no output schema, the description provides enough for agent understanding. Could mention response fields but not essential.

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 has 0% description coverage for parameter 'q', but the description explains 'q' filters over topic/title/description, adding crucial 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 tool lists groups by topic, not by person, and provides filtering with 'q'. It distinguishes from a person-based 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?

Implies when to use (by topic) and when not (by person), but does not explicitly list alternatives or provide comprehensive when/not scenario.

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, but description discloses critical behavior: private key returned once and never stored server-side. This adds significant 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 clear, front-loaded sentences. 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?

Despite no output schema, description explains return values and the one-time private key delivery, which is sufficient for a no-param creation 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?

No parameters, so schema coverage is complete. Description adds value by detailing output shape and key behavior.

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 mints a sovereign, portable identity and lists return fields. No sibling tools do the same, so it's well-differentiated.

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 creation usage with 'hand it to the user and forget it', but no explicit when-to-use or when-not-to-use 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?

No annotations are provided, so the description carries the full burden. It discloses that the operation is deterministic and yields a stable fingerprint, which are useful behavioral traits. However, it does not describe any side effects, permissions, or output format, leaving some 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 is a single, well-structured sentence that front-loads the key verb and resource. Every word 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?

For a simple tool with one parameter and no output schema, the description adequately identifies the core functionality. However, it lacks details on input format and output characteristics, which are important for correct invocation.

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 low coverage (0%) and the description adds no additional meaning about the 'public_key' parameter beyond its name. It does not specify format, encoding, or examples, which is insufficient for an agent to correctly format the input.

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 ('Derive'), the resource ('stable public fingerprint id from a public key'), and a key property ('deterministic'). It is specific and distinct from sibling tools like identity_create or identity_verify.

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, nor any prerequisites or limitations. It merely implies usage when a public key is available and a fingerprint is needed, which is minimal.

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 discloses the key behavioral trait: 'never raises; True/False'. However, it leaves out other behaviors such as handling of invalid keys or message encoding, which would be helpful for an 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 extremely concise with two sentences, front-loaded with the verb and resource. 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 verification tool, the description covers the core behavior and return value. However, it lacks differentiation from siblings like 'verify' and does not elaborate on edge cases or the meaning of 'never raises'. No output schema exists.

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 names (sig, message, public_key). The agent gains no insight into format, encoding, 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?

Description clearly states the verb 'Verify', the resource 'a signature over a message against a public key', and the behavior 'never raises; True/False'. It is specific and distinguishes from siblings like 'verify' by focusing on signature verification.

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 through the action 'Verify' and mentions 'never raises', but does not explicitly state when to use this tool versus alternatives like 'verify' or 'badges_verify'. 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 provided. The description only hints that the tool 'is the keeping loaded and sound' without disclosing what the tool does (e.g., check status, repair, etc.) or 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?

The description is very short (one sentence), but it is awkwardly phrased and unclear, diminishing its effectiveness.

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 no output schema and no parameters. The description does not explain what the tool returns or provides sufficient context for an agent to understand its 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?

No parameters in the schema. The description does not need to add parameter meaning, and baseline is 4 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?

The description vaguely indicates a health check for a corpus, referencing 'totals, shelves, surfaces' but does not clearly state what action the tool performs. It is not a tautology but lacks precision.

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. The description does not mention any 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?

With no annotations, the description carries full burden. It discloses the matching strategy (exact ID, then title, then ranked search), which is a key behavioral trait. However, it omits potential error cases or output 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?

A single sentence with front-loaded purpose. No wasted words; every part 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?

The description explains the matching strategy well but lacks return value details (no output schema) and error handling, leaving some context incomplete for an agent to fully understand the tool's 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 parameter 'q' has no schema description (0% coverage). The description adds meaning by clarifying that 'q' can be an ID, title, or query, guiding the agent's input.

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 finds a card for a query, with a specific fallback strategy: exact ID, then title, else ranked search. This distinguishes it from siblings like 'search' (broader) and 'card_get' (ID-specific).

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 locating a card by query, but does not explicitly provide when-not-to-use or alternatives. A clear context is given, but lacks direct 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 must disclose behavioral traits. It reveals the synthetic nature but does not mention other important aspects like language support, accuracy, processing time, or any limitations. More transparency 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?

The description is a single sentence that efficiently conveys the tool's purpose and key trait (synthetic). It is front-loaded and avoids unnecessary words, though the dash-separated clause could be integrated.

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 low complexity, the description should mention what the tool returns. It does not specify the output format or any error handling. Additional context about language support or limitations is missing.

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. It adds meaning by stating the input should be a 'transliteration or word,' which helps clarify the 'text' parameter. However, it does not provide examples or further 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 the tool provides a synthesized pronunciation guide with respelling and approximate IPA. It specifies the input is a transliteration or word and honestly labels it as synthetic. Sibling tools appear unrelated, so no need for differentiation.

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. There is no mention of prerequisites, context, or when not to use it. The description only states function, not 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 provided, so description carries full burden. It discloses deterministic behavior, data never leaves machine when run locally, and returns mapping. Could be more explicit about side effects, but overall 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?

Two sentences, front-loaded with action and examples. No wasted words, each sentence adds value. Excellent structure.

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 one parameter and no output schema. Description explains behavior, privacy, and pairing with verify. Minor gap: return value format (mapping) not detailed, but adequate for 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 coverage is 0%, but description compensates by specifying 'from text' making the single parameter clear. No additional details on text format or constraints, 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 tool strips PII (emails, SSNs, credit cards, IPs, URLs) from text, replacing with stable placeholders and returning a mapping. It distinguishes itself from siblings by mentioning pairing with 'verify' and running locally.

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 guides when to use ('before you pass it onward'), recommends local/sovereign engine for privacy, and suggests pairing with 'verify' for a receipt. No alternative tools mentioned but 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, and the description only says 'Fetch', implying a read operation. However, it does not disclose authorization requirements, expected behavior on missing hashes, or whether the operation is 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, clear sentence with no redundant information. It is front-loaded and efficient.

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 fetch tool with one parameter and no output schema, the description covers the basic operation but omits details about return format, domain knowledge (what a sealed record is), and error handling.

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 description adds context that the 'hash' parameter refers to 'content hash', which is not in the schema. However, it lacks details like format or constraints, and several sibling parameters are not described.

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 ('Fetch'), the resource ('sealed verification record (the receipt)'), and the input ('content hash'). It implicitly distinguishes from sibling tools like 'verify' by specifying the resource type.

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., 'verify', 'audit'). No preconditions 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?

Without annotations, the description must disclose behavior. It mentions 'Ranked search' but does not specify if it is read-only, side effects, or how ranking works. No details on constraints or error conditions.

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 under-specified. It lacks necessary details, making it not 'efficient' but rather insufficient for safe tool use.

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 minimal parameter information, the description fails to convey return format, pagination, errors, or authentication needs. It is incomplete for a search 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 for parameters. The description does not explain 'query' or 'limit' beyond their names, leaving the agent to guess format, default for limit, or allowed query types.

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 'Ranked search over the keeping (the kept library)', which identifies the tool as a search function with ranked results. However, 'the keeping' is unclear without context, and there is no differentiation from sibling tools like 'locate' or 'cards_browse'.

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. Siblings like 'locate' or 'cards_browse' may overlap, but the description offers no context for selection.

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 reveals the record type is distinct and cannot count as a sealed check or satisfy auto-graded requirements. But it does not disclose other behavioral traits like permissions, side effects, or whether this is a create operation. 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?

Single sentence, no redundancy, front-loaded with key purpose. Every word contributes meaning.

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 3-parameter tool with no output schema and no annotations, the description provides the core intent and a key behavioral constraint, but lacks details on parameter syntax, output, or prerequisites. Adequate but not fully 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 0%, so description must compensate. It implies 'study' is the study context, 'statement' the words, and 'subject_id' the person, but does not explicitly define each parameter. Adds some meaning but not enough for full 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?

Description clearly states the tool records a person's own words about their study, with explicit distinctness from verification tools. It uses specific verb 'Record' and resource 'person's OWN words', and distinguishes from siblings like 'seal_fetch' and 'verify'.

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?

Description explains what the tool does and that it cannot be used for sealed checks or auto-graded requirements, providing a clear exclusion. However, it lacks explicit guidance on when to use it vs. alternatives like 'study_create' or 'audit', leaving the agent to infer.

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 reveals a key behavioral trait (NEVER moves money) but lacks details on side effects, authentication, or output format. Without annotations, more transparency 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 with a parenthetical that covers purpose, inputs, outputs, and constraints. No unnecessary words; front-loaded with the tool name and role.

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 offers sufficient context for a simple calculation tool with no output schema. It explains inputs and outputs qualitatively but omits details on expense array structure or return format. Minor gap.

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 has 0% description coverage, so the description compensates by explaining that 'income' and 'expenses' inputs produce net, savings rate, and category breakdown. This adds meaning beyond bare schema types.

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: household budget computation (income, expenses -> net, savings rate, by category). It distinguishes from siblings by declaring it never moves money, contrasting with steward_cost_destroyed.

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 (budget planning) and explicitly states it shows/plans and never moves money, providing context. It does not explicitly list alternatives but is clear enough.

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 disclose behavioral traits like idempotency, side effects, or permission requirements. It only mentions 'money you did NOT spend', leaving mutability and read/write nature unclear.

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 short but under-specifies the tool. Conciseness is not helpful if it omits 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 simple schema (one array param) and no output schema, the description still fails to provide enough context for correct invocation. It does not explain what the tool returns or how to construct the 'items' 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?

The input schema has one required array parameter 'items' with no description. The tool description adds no information about what 'items' should contain, such as expected structure or format. Schema coverage is 0% and description fails to compensate.

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 'money you did NOT spend (was -> now), kept in your currency' lacks a clear verb and does not specify whether the tool computes, records, or lists cost destroyed. It is vague and does not differentiate from sibling tools like steward_budget.

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 usage guidance is provided. The description does not indicate when to use this tool versus alternatives (e.g., steward_budget) or any 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?

Describes non-duplication, one card per entry, and key-based reference, but misses details about authentication, rate limits, or meaning of 'lives once'. With no annotations, it partially reveals 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?

Single sentence packed with key information, no fluff. Front-loaded with action and resource.

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 2 params, no output schema, and no annotations, the description is incomplete. It does not explain the key parameter, card structure, or how to extend a study.

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 has 2 params (key and cards) with 0% description coverage; the description does not explain either parameter, failing to add value 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 clearly states the action (create/extend), the resource (shared study with superposition stack), and distinguishes from siblings by emphasizing single card minting and no duplication. It is specific and unique.

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. Implies usage for creating studies but lacks explicit context 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 carries the full burden. It mentions optional signing, hinting at cryptographic behavior if private_key is provided. However, it does not disclose the bundle format, whether the operation is destructive, or any side effects on the study. Some key behavioral traits are omitted.

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 front-loads the verb and resource. It is concise and contains no fluff, though it could add a second sentence for key details 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 two parameters, no output schema, and no annotations, the description is too brief. It does not explain the output format, what the bundle contains, or how to use the exported data. For an export tool, this is insufficient for an agent to fully understand the tool's 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?

The input schema has 0% description coverage, and the description only adds meaning for the private_key parameter ('optionally signed'). The key parameter is not explained (likely a study identifier). This is minimal added value 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 clearly states the verb 'Export' and the resource 'study', and specifies that it produces a 'self-contained, portable bundle' with optional signing. This is specific and informative, though it does not explicitly differentiate from sibling tools like study_create or study_import.

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 (e.g., study_create, study_import). It does not mention typical use cases like backup, sharing, or migration, leaving the agent without context for selection.

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 transparency burden. It discloses that the tool re-materializes cards and ensures uniqueness, but omits details on error handling, idempotency, authorization needs, or what happens if the bundle already exists.

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, front-loaded sentence with no redundancy. Every word contributes meaning.

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 3 parameters, a nested object, and no output schema, the description is very terse. It does not explain the structure of the bundle, the purpose of key and verify_signature, or what the tool returns, 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 0%, and the description adds no explanation for the three parameters (key, bundle, verify_signature). The agent must infer meaning from names alone, which is insufficient for correct use.

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 imports a study bundle and re-materializes its cards, with a notable uniqueness constraint (each card lives once). This distinguishes it from siblings like study_create and study_export.

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 restoring a previously exported study, but it does not explicitly state when to use this tool over alternatives (e.g., study_create for new studies) and provides no when-not 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?

With no annotations, the description carries full behavioral transparency. It discloses the deterministic nature, the elimination method ('eliminates what is not the answer'), and the return structure (verdict, trail, seal). It also mentions the seal's re-verification via 'seal_fetch'. No contradictions with annotations as none exist.

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 concise given the complexity, with each sentence adding new information. It front-loads the core purpose and then details forms and domain coverage. It could be slightly tighter, but no extraneous content 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?

For a tool with no output schema, two input forms, and nested objects, the description is remarkably complete. It covers return values, input structures, domain coverage, and hints at related tools. No critical gaps are apparent.

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 significant meaning: explaining the two forms, how the 'steps' array should be structured for domain-specific packets, and the purpose of the 'seal' parameter. This integrates the parameters into a coherent workflow beyond their individual schema 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 the tool's purpose: 'Verify a claim deterministically' and describes two input forms (MATH and ANY DOMAIN). It also mentions the output elements (verdict, trail, receipt). However, it does not explicitly distinguish from sibling tools like 'audit' or 'identity_verify', relying on the mention of 'seal_fetch' as a related tool.

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 guidance on when to use each form (MATH vs ANY DOMAIN) and directs users to 'find_verifier(keyword)' for domain selection. However, it does not specify when not to use this tool or compare it directly with alternatives, 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.