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

Annotations cover safety (readOnly, idempotent) and open-world scoping, so the description doesn't need to re-explain those. The description adds useful behavioral detail: results sorted newest first, q matches title only (not companies/people), and phrasing guidance for citing url/updated_at. It doesn't mention pagination behavior or rate limits, but annotations already handle the core safety profile.

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?

Very dense and front-loaded. Each clause packs meaning, though sentence structure is a bit choppy with many semicolons and could be slightly more organized. No filler whatsoever.

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 complex 11-param search tool with no output schema, the description covers the most critical filter semantics, sorting, and citation behavior. It's missing guidance on pagination limits and the type/status parameters, but overall it provides the necessary context for correct invocation.

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 64%, so the description carries some of the load. It clarifies q is title-only, enumerates stage values, explains city/state/country semantics with examples, and defines since/updated_since precisely. However, it doesn't cover page, limit, type, or status parameters, leaving gaps for a tool with 11 parameters.

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: 'Search or filter film and TV productions.' Clearly distinguishes from get_production (single lookup) and search_companies (different resource), though it doesn't explicitly say it only returns productions matching filters vs. a full list.

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?

Gives explicit routing for common queries: stage=in-production for 'what is filming now,' stage=in-pre-production for 'what is coming.' Names the fields to cite. Doesn't explicitly say when to use this tool vs. sibling tools, but for a search endpoint the use case is self-evident.

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