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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description still adds substantive context: paused or closed programs are omitted, provider/program names match only programs carrying that name while topics also match the covering category, rarer words weigh more, and results are capped at 25 with a page link. These are non-obvious retrieval behaviors an agent could not infer from the annotations or schema.

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?

Purpose and usage examples are front-loaded, and the matching rules and result shape follow in logical order. The middle sentence is a dense semicolon-chained run-on that takes a second pass to parse, but no sentence is 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?

For a six-parameter search tool with no output schema, the description supplies what the agent needs: how matching works, what is filtered out, and what a result row contains (stated value, primary eligibility gate, links, plus a page to browse more). Nothing material is left to inference.

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 baseline is 3, and the description genuinely adds meaning beyond it: it explains how the query string is interpreted (name match vs topic-to-category expansion, rare-word weighting) and clarifies that open_to_any_startup means no investor, accelerator or referral requirement. It does not restate the limit, min_value_usd or enum semantics, but those are already well documented in 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 opens with a specific verb and resource ("Search the catalog of 2,800+ startup programs") and names the facets it searches over (provider, program, topic). It explicitly routes the agent away from the sibling find_startup_perks for the alternate case, so the tool is distinguishable without opening any schema.

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?

Concrete example questions ("Does Stripe have a startup program?", "Which providers give GPU credits?") plus browsing scenarios (category, benefit type, open-to-any-startup) cover the main intents. The exclusion is explicit: use find_startup_perks when the user wants what a specific company qualifies for.

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