GimmeTheSauce

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is fully covered. The description adds genuine context beyond that — the data source ("Sauce catalog") and the shape of returned entities — but says nothing about ranking, pagination behavior, or what an empty result looks like.

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 search capability, with no filler or redundant phrasing. The second sentence earns its place because no output schema exists to describe the return values, though it could carry slightly more operational detail at the same length.

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

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

For a four-parameter search tool with no output schema and zero schema description coverage, the description is thin. It explains the entity being searched and the return shape but leaves the enum semantics, pagination controls, and default result count entirely undisclosed, so an agent cannot reason about how to page or how to constrain result type.

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% across four parameters, so the description carries the full burden and largely drops it. "By public name, product or topic" glosses the query field and "founders and specialists" loosely maps to the kind enum, but limit and offset are never mentioned and the enum's two values are not explained, leaving half the parameters undocumented in both places.

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 pairs a specific verb ("Find") with a concrete resource ("founders and specialists") and states the searchable facets (public name, product, topic) plus the returned fields (names, research IDs, specialties). It is clearly distinct from search_sources in subject matter, though it never names that sibling to make the contrast 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 only implied: an agent can infer this is the tool for locating people in the catalog when it knows a name or topic. There is no statement of when to prefer it over search_sources, no note on prerequisites, and no guidance about behavior when the query is too broad or returns many matches.

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, so the safety profile is covered. The description usefully adds that results come 'from the indexed library' (confirming a curated corpus rather than live web search) and sketches the return shape (links, dated labels, summaries), but says nothing about result capping 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?

Two short sentences, front-loaded with the action and scope, and the second sentence efficiently covers returns. Nothing is padded, though 'dated evidence labels' is mildly jargonistic without further 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?

With no output schema, the description does the right thing by describing returned fields, and it scopes the search to one mentor. It is still incomplete for a required-slug tool: how an agent obtains a valid slug and how limit affects results are both left open.

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 carries the full burden. 'One mentor and topic' does imply that slug is a single mentor identifier and query is the topic, which is real added meaning, but the slug format, where to get it, and the existence and cap of the limit parameter (default 5, max 8) are all unstated.

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 ('look up public research') and resource ('sources' about 'one mentor and topic'), which lets an agent distinguish it from find_mentors (which returns mentors rather than evidence). It never names the sibling explicitly, so differentiation is inferred rather than stated.

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 'about one mentor and topic' implies the call pattern (single mentor per query) but there is no explicit when-to-use guidance, no prerequisites, and no mention of when to prefer find_mentors first to obtain a slug. Usage is implied, not directed.

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