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

Annotations only declare readOnlyHint and openWorldHint, so the description earns credit for disclosing auth ('Needs an API key'), per-call cost ('billed per search'), result ordering ('newest relevance first'), and a 20-per-page result cap. These are traits an agent cannot get from structured fields. It stops short of covering failure modes, empty results, or rate limiting.

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 dense sentences with no filler: purpose and return shape first, then filters, then the cost/auth caveat last. Every clause carries distinct information.

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 covers the return shape, ordering, and page size, which is what an agent needs before calling. It is slightly thin on how to paginate past the first page and has no mention of what happens on auth failure or zero 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 20% — only 'podcast' is documented in-schema — so the description has to carry real weight. It adds the date format (YYYY-MM-DD), the scope of the podcast filter, and pagination behavior ('20 a page'), but never explains the required 'query' field's matching semantics or how 'page' interacts with the 20-per-page limit.

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 ('Full-text search across transcripts') plus the return shape ('matching episodes with snippets'), which clearly separates it from single-record tooling. It never names the sibling it contrasts with (get_transcript, ask_question), 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?

It gives some routing signal via 'see list_services' for billing and frames the optional filters as narrowing scope. But it never says when to choose this over ask_question or get_transcript, and no exclusions or prerequisites are spelled out beyond needing an API key.

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