Pick My Costume

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered. The description earns credit for adding behavior beyond that: it specifies exactly what the response contains, which matters because there is no output schema. It does not address error cases such as an unknown id or an ambiguous name match, which keeps it short of a 5.

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, the payload list front-loaded, no filler or hedging. The enumerated return contents are long but each item carries information; the only minor weakness is that the parameter sentence trails as an afterthought rather than being 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?

For a single-parameter read tool with no output schema, the description does the essential work by describing the returned structure. Combined with complete annotations and full schema coverage, an agent has enough to call it correctly; only ambiguity/error behavior is unaddressed.

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

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

Schema coverage is 100% and the single parameter already documents both accepted forms (id or name) with examples. The description restates the id-or-name duality without adding format or resolution rules for name matching, so it sits at the baseline for a fully documented 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 opens with a specific verb and resource ("Returns the step-by-step build instructions for one costume idea") and enumerates the payload (decision summary, materials with buy-vs-own tags, numbered steps, safety notes, parent Q&A). That clearly separates it from pick_costume and search_by_owning, though it never names the siblings to make the distinction explicit.

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

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

Usage is implied rather than stated: the schema reference to "idea id from pick_costume" sketches the natural flow (pick, then fetch the guide), but the description never says when to choose this tool over a search, nor what to do if the user only has a vague costume concept. Adequate but inferential.

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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description adds real behavior beyond that: the catalog is fixed at 169, output is capped at top 3, and ranking weights (interest strongest, owned items boost). It does not discuss tie-breaking or what happens when nothing matches well.

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?

Front-loaded with the ranking action and output count, then the return payload, then ranking rules. Slightly repetitive in restating the interest signal that the schema also states, but no filler.

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

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

No output schema exists, so the description correctly spells out the return payload (why-line, thumbnail, build-page link, time/effort estimate). For a 6-parameter read-only recommender this is nearly complete, missing only behavior on empty or poor matches.

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

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

Schema coverage is 100% and the schema already documents every parameter including that interest is 'the strongest ranking signal'. The description restates that weighting and adds that owned items raise rank, so it adds modest meaning but largely mirrors 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?

States a specific verb and resource ('ranks Halloween costume ideas from a fixed catalog of 169') plus the exact output shape (top 3 matches). An agent can tell this apart from get_build_guide and search_by_owning purely from this sentence.

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 use case (ranking candidate costumes from audience/interests/vibe/effort/materials), but never states when to choose this over search_by_owning or get_build_guide, nor any exclusions. The mention of a 'link to its full build page' only hints at the get_build_guide handoff.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real value on top: it discloses the ranking order, the tag vocabulary attached to each still-needed item (buy/own/either/make), and the important behavioral assumption that common household basics are treated as present. It stops short of describing result volume, pagination, or empty-result 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?

Three tight sentences: ranking rule first, then result shape and tags, then the assumption and audience caveat. Nearly every sentence earns its place, with only mild duplication of the 'assumed list is returned' claim that the schema also states.

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

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

With no output schema, the description carries the return-value burden and does so: it explains the ordering, that each result shows remaining needs, and the tag taxonomy on those needs. Combined with annotations covering safety and a fully documented 2-parameter schema, an agent has everything needed to call this 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 description coverage is 100%, and the schema already documents both the items array and the assumed-basics behavior plus the who_for narrowing, so the description largely restates structured data. It confirms the ranking semantics that give 'items' meaning but adds no new syntax or format detail. Baseline 3 applies.

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

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

The description names a specific operation — ranking the fixed costume catalog by how much of each idea's material list is already covered by the supplied household items — and states the ranking rule (least extra shopping first). That is enough to separate it from get_build_guide and pick_costume, though it never names those siblings explicitly.

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

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

The framing ('so ideas needing the least extra shopping rank highest') makes the intended use case reasonably clear, and the optional audience parameter's narrowing effect is stated. However, there is no explicit when-to-use versus when-to-use-a-sibling guidance and no exclusions, so routing between this and pick_costume is left to inference.

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