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

With no annotations, the description carries the full burden of behavioral disclosure. It does explain what data is included, but it does not explicitly state that this is a read-only operation or describe behavior for a non-existent garment ID.

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 core purpose ('Full record for one garment') and then lists the key inclusions. There is no wasted wording.

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 single-ID fetch with no output schema, the description adequately communicates what the caller should expect: attributes, views with provenance, and file paths. It could be more complete by noting the response format or error handling, but the essentials are present.

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

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

Schema description coverage is 100%; the only parameter, garment_id, is documented with an example. The description adds no additional parameter guidance, which is acceptable given the high schema coverage.

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

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

The description clearly identifies the resource (one garment) and the scope of what is returned (all attributes, every view with provenance, and file paths). It distinguishes itself from list/search siblings by emphasizing a single full record, though it lacks an explicit verb like 'returns'.

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 phrase 'for one garment' implies this is the tool to use when a specific garment ID is already known and complete details are needed. However, it does not explicitly state when to prefer this over list_garments or search_garments, nor does it provide 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 behavioral burden. It clearly states 'Read', indicating a read-only operation. It also adds conditionality ('where a cost attribute exists'), which warns the agent that cost-per-wear is not always returned. It does not mention potential edge cases like empty results or default date ranges, but for a read tool the core effect is disclosed.

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 one clear sentence that front-loads the core purpose ('Read the wear log'). The list of output items makes it longer, but every phrase adds relevant information, and there is no wordiness or repetition.

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

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

Given there is no output schema, the agent cannot verify the response shape from structured data, and the description does not describe the exact structure. It says what is returned but not in what form (e.g., array vs. nested object), nor does it clarify what happens with the date range or garment_id filters. It is adequate but not fully self-reliant.

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

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

The input schema already describes the three parameters with 100% coverage, so the baseline is 3. The description adds little beyond the schema: it does not explain how since/until/garment_id interact or affect the return, so it does not meaningfully enrich parameter semantics.

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 begins with the specific verb 'Read' and identifies the resource 'the wear log'. It then enumerates the distinct outputs it returns (individual entries, per-garment totals, first/last worn, never-worn items, cost-per-wear), which makes it easy to distinguish from get_garment (garment details) and log_wear (writing a wear entry).

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 reading wear history, but it does not explicitly state when to choose this tool over siblings like log_wear or search_garments. It names no exclusions or 'when-not-to-use' conditions, so guidance is only implied.

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 at all, the description carries the full burden of behavioral disclosure. It conveys that the tool is an introspective lookup and implies a read-only nature, but it does not explicitly state that it has no side effects or describe pagination/size behavior. This is adequate but not rich.

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

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

Two short sentences carry both purpose and usage guidance with no filler. The directive 'Call this before guessing filter values' earns its place by making the use case actionable.

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

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

For a zero-parameter, no-output-schema tool, the description is nearly complete: it says what the tool returns at a conceptual level and when to call it. A slight gap is the lack of any indication of the exact response shape, but the description's conceptual framing is sufficient for a metadata listing.

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 takes zero parameters, so parameter documentation is irrelevant; the baseline for this dimension is 4. The description adds context by linking the output to filter values, which is all an agent needs here.

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 identifies the resource ('attributes this catalogue actually carries') and the operation (reporting what values they take), which clearly distinguishes it from sibling tools like list_garments and search_garments. It goes beyond the tool name by adding the crucial 'actually carries' scope.

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?

'Call this before guessing filter values' is an explicit when-to-use directive that tells the agent to invoke this tool before constructing filters. It does not explicitly name sibling alternatives or state when not to use it, but the use case is unmistakable.

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 behavioral disclosure burden. It does a good job by revealing that records are compact (not full details) and that the result set is paginated via limit/offset. It does not mention other behavioral aspects like ordering or error handling, but for a read-only list operation these are less critical.

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?

Three concise sentences, each earning its place: the first states the core action, the second differentiates from get_garmenteb, and the third explains pagination. No redundant or vague content, and the most important purpose is front-loaded.

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

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

The description covers the essential aspects for using the tool: what it lists, that it is filterable, that the response is compact, and how pagination works. The schema fills in parameter details scrape. The only noticeable gap is not explaining when to prefer search_garments over this tool, and the output schema is absent so the exact shape of 'compact records' is unspecified, but the pointer to get_garment mitigates this.

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

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

The schema already describes four parameters (colour, season, category, attributes) with examples, but limit and offset lack descriptions. The description compensates by explicitly identifying limit/offset as pagination controls, and it also confirms that filtering is optional without repeating the schema details. This adds meaningful context 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 uses a specific verb ('List') with a clear resource ('garments in the wardrobe') and notes optional filtering. It explicitly distinguishes itself from get_garment by stating that list_garments returns compact records, which allows an agent to select the correct tool immediately.

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

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

It explicitly instructs to 'use get_garment for full detail', giving a clear when-not-to-use condition. However, it does not address the search_garments sibling, which could be an alternative for more complex queries, leaving some ambiguity about when to choose this over search_garments.

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 behavioral burden and does well: it states the operation is append-only ('Appends to the wear log'), limits side effects ('never modifies the catalogue'), and exposes the date default behavior. It does not mention return values or permission requirements, but the core mutation behavior is 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?

Three short sentences, no filler. The primary action, side-effect constraint, and date default are each given their own sentence and are front-loaded.

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

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

For a three-parameter append tool, the core facts are covered: what action is performed, that it does not touch the catalogue, and the optional date behavior. The main gap is lack of any hint about the note parameter or the returned result, but neither is critical for a minimal correct call.

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 low (33%), and the description compensates only partially. 'Date defaults to today' adds real meaning beyond the schema, and 'Record that a garment was worn' contextualizes garment_id, but the note parameter receives no semantic guidance. This is adequate but incomplete.

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 opens with a concrete verb and object—'Record that a garment was worn'—and clarifies the target is the wear log, not the catalogue. This clearly differentiates it from siblings like get_wear_history and list_garments.

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 establishes when to use it: any time a wear event should be appended, with date defaulting to today. It does not explicitly name alternatives or exclusions, but the 'never modifies the catalogue' contrast provides useful context for choosing it over catalogue operations.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It mentions 'returns compact records, best match first', which gives some insight into return format and ordering. However, it does not disclose any side effects (likely read-only) or pagination details. A search operation is typically safe, but without annotations, more explicit confirmation would be helpful.

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 and front-loaded with the core purpose in the first clause. It wastes no words and gets straight to the point, though it is slightly sparse.

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 relative simplicity (2 parameters, no nested objects, no output schema), the description is nearly adequate. However, it lacks any note on limit behavior or match criteria. With no annotations or output schema, the description could be improved by adding a note on result order and limit usage. It is functional but leaves room for agent uncertainty.

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

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

Schema description coverage is 0%, so the description must compensate for the lack of parameter documentation. It only correlates to the 'query' parameter by saying 'free-text search over names, descriptions, and attributes', but it does not explain the 'limit' parameter's meaning or that it controls result count. The default value of 20 is in the schema, but the description adds little clarity for either parameter.

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

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

The description clearly states the action (free-text search) and the resource (garments), specifying that it searches over names, descriptions, and attributes. It distinguishes from siblings like list_garments and get_garment by focusing on free-text search and compact records, though it could be more explicit about how it differs from search_narration.

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 it (for free-text search across fields) but provides no explicit guidance on when not to use it or alternatives. It does not mention that list_garments might be better for browsing or get_garment for retrieving a specific record, but the sibling names give context.

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

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

No annotations are provided, so the description must carry the burden of behavioral disclosure. It is clearly a search/read operation (no mutation hinted), and it explains the type of data accessed (narration from filming) and the filter dimensions (field enum values). However, it does not explicitly state that the operation is side-effect-free, nor does it mention any rate limits, authentication requirements, or error behavior. Since it's a search, the lack of explicit read-only statement is a moderate gap.

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

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

Two sentences with no filler. The primary purpose and scope are front-loaded, and the usage guidance is delivered in a compound sentence. Every clause earns its place.

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

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

The description gives a clear picture of what the tool searches and when to use it vs. the sibling. However, with no output schema, the description does not explain the return value structure (e.g., it likely returns a list of narration snippets or matching records). The agent is left to infer the output format, which is a notable gap for a tool with no output schema.

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

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

Schema coverage is only 33%, so the description must compensate. It does explain the meaning of the search query ('materials, where things came from, how they feel') and maps to the field enum values (material, provenance, sentiment), adding semantics beyond the schema's brief field description. However, it does not address the 'limit' parameter or elaborate on the 'query' format, leaving those parameters under-documented at a time when schema coverage is low.

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

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

The description clearly states a specific verb ('Search') and resource ('what the wearer said about their clothes while filming'), and immediately distinguishes it from the sibling search_garments by noting the alternative for appearance-related questions. It names the content domains (materials, provenance, sentiment), so the agent can tell exactly what this tool does.

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

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

The description explicitly provides when-to-use guidance ('questions about history, feelings or origin') and names the alternative tool (search_garments) for appearance questions. This gives the agent a clear decision rule without needing to inspect sibling schemas.

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