Present Picker

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description still adds real value by disclosing the no-match behavior ('the result says so and gives example ids') and by enumerating the response payload in the absence of an output schema. It does not clarify name-matching semantics (fuzzy vs exact) or case sensitivity.

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 purpose, then the field list, then fallback behavior — a sensible order. The long mid-sentence enumeration of return fields is justified because no output schema exists, though the opening tagline ('Picked for them, not the store') spends words on flavor rather than function.

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 correctly carries the burden of describing the return payload and the empty-match case, which is the right allocation of effort for a one-parameter read tool. Minor gaps remain around name-matching rules and invalid-id 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?

Schema description coverage is 100%, so the single parameter is already fully documented. The description's mention of ids from pick_gift/search_gifts and the 'cast iron skillet' name example essentially restates the schema text, adding no new syntax or format 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?

States a specific verb and resource ('returns the full detail for one gift idea from the bank') and immediately enumerates the returned fields, so the agent knows exactly what this yields versus the sibling pick/search tools. The scope — one gift, by id or name — is unambiguous.

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?

Names the upstream sources of the identifier ('a gift id returned by pick_gift or search_gifts'), which implicitly routes the agent: find a gift with a sibling, then fetch details here. It does not explicitly say when NOT to use it (e.g., 'use search_gifts to browse'), so the routing is inferable rather than spelled out.

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?

Beyond the read-only, closed-world, idempotent annotations, the description discloses extensive behavior: the 255-idea bank, max 5 results, ranking rules, hard-filter semantics, recipient shelf mapping, keyword-miss behavior, and what the result includes. This is unusually transparent for an agent deciding how the tool will behave.

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 front-loaded with what the tool returns, which is good, but it is a very long dense paragraph. Many details are useful, yet the single-block structure and repeated filter/result explanations make it harder to scan than it needs to be.

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 burden of explaining the return shape and does so thoroughly: picks, one-line descriptions, why-lines, buying notes, lead_pick, more_ideas, answer_text, and metadata fields. It also covers recipient mapping, hard filters, misses, and fewer-than-five-result cases, so an agent has enough context to call 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?

Although the schema has 100% description coverage, the description adds substantial cross-parameter meaning: style and budget act as hard filters, interests affect ranking, keyword matching ranks first and changes lead_pick behavior, exclude drops matching picks, and recipient values like 'teen' and 'coworker' trigger special mapping. These are semantic interactions the schema alone does not capture.

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 a specific verb and resource: it returns up to 5 gift ideas from a fixed bank, matched to recipient, budget, interests, and optional style. It is clear what the tool does, but it never names or distinguishes the sibling tools get_gift and search_gifts.

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 gives clear invocation context by explaining hard filters, ranking behavior, recipient-only sampler behavior, and edge cases like keyword misses and excluded items. It does not explicitly say when to use pick_gift instead of get_gift or search_gifts, so it stops short of full alternative routing.

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 read-only, idempotent, non-destructive and closed-world, yet the description adds real behavior: results come back in fixed bank order, capped at 10, and the response reports the total match count even when it is zero. It also enumerates the per-result payload (one-line description, why-line, buying note, budget band, photo link, deep link), which removes any ambiguity about what a call yields.

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 the core operation and followed by the return contract; nearly every clause carries information. The opening tagline 'Picked for them, not the store:' is the one piece of framing that does not earn its space against an otherwise dense, functional description.

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 five optional parameters, no required inputs, no output schema and annotations already stating the safety profile, the description supplies exactly the missing pieces: the data source size, result ordering and cap, and the shape and count semantics of the response. An agent has everything needed to call this correctly and interpret the output.

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

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

Schema coverage is 100%, so every parameter including the budget bands, recipient set and interest list is already documented in structured form, making 3 the baseline. The description only adds the combinability hint ('by interest, by keyword, or by both') and the general filter framing, without going beyond the schema on limit or budget 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 gives a specific verb and resource — 'searches the fixed bank of 255 gift ideas' — plus the search axes (interest, keyword, both) and filter dimensions, so the scope is unambiguous. It never names the siblings get_gift or pick_gift, so the boundary between 'search many' and 'fetch/choose one' is left for the agent to infer from the names.

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?

'by interest, by keyword, or by both' implies the main usage modes, and the recipient/budget filters hint at narrowing use cases. However there is no explicit when-to-use guidance, no statement of when to prefer get_gift or pick_gift instead, and no prerequisites or exclusions.

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