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

Annotations already signal read-only, non-destructive, and closed-world behavior, but the description adds significant context beyond them: the guide's curated nature means absence is meaningful, empty results are honest answers rather than errors, and free text is resolved to the guide's own vocabulary with the interpretation reported back. This is exactly the kind of behavioral nuance an agent needs.

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 longer than typical, but every sentence earns its place: it conveys the curation philosophy, the closed-world semantics, when to reach for the tool, when not to, and how q behaves. It is front-loaded with the core purpose and quickly moves to actionable usage guidance.

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 17-parameter search tool with no output schema, the description covers the essential context: curated scope, empty-result semantics, q resolution, and the distinction from a comprehensive database. It does not explain how multiple filters combine or what the response shape looks like, but the schema covers cursor and limit, and the description covers the behavioral pitfalls that matter most.

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 71% and the individual parameter descriptions already do most of the work, explaining city slugs, area scoping, price bands, cuisine composition, and cursor binding. The tool description adds a useful semantic note about q being resolved to the guide's vocabulary, but most parameter meaning lives in the schema itself, so the description adds only marginal value beyond it.

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 the Max Eats Out guide', and immediately differentiates it from a generic places database by calling it 'editorially curated' with 'a point of view'. It clearly identifies what the tool is for, unlike the sibling lookup tools, and the phrase 'never present an empty result as there are no restaurants there' sharpens the intended use.

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 when-to-use guidance: 'Reach for this when someone wants a recommendation with an opinion attached' or wants to filter by editorial qualities like Best For and Michelin awards. It also gives an explicit when-not-to-use: 'Do not reach for it to find the nearest branch of a chain.' However, it does not name a sibling tool as the alternative, so the routing is not quite complete.

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