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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavioral context beyond that by revealing that the tool accepts free-form, subjective language ('in their own words', 'feeling') and matches books thematically rather than by exact metadata. It doesn't describe return format, but that is a minor gap for a read-only recommendation tool.

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?

Three sentences, all useful: function, use cases/examples, and sibling routing. Ideas are front-loaded and there is no filler or redundant restating of the title or schema.

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?

The tool is simple (three params, one required, read-only) and the description covers the primary input thoroughly, gives examples, and names the alternative for a different scenario. The only notable omissions are explicit semantics for the optional isFiction/limit and return value shape, which are not essential but would make it fully complete.

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?

With schema description coverage at only 33%, the description carries extra weight. It adds rich semantics for the required description parameter via examples ('books about grief', 'cozy mysteries set in Cornwall'), but gives no extra meaning for limit and isFiction, which have no schema descriptions. Their names are somewhat self-explanatory, but isFiction's filtering behavior is still ambiguous.

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 clear action—turn a user's own description of a mood/theme into book recommendations—and distinguishes itself from sibling search_books ('Use search_books instead when you already know the title or author'). The sibling name recommend_from_titles further reinforces the unique niche, so there is no ambiguity about what this tool does.

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?

Explicitly gives the use case ('Use this for a theme, subject or feeling') and the alternative condition ('Use search_books instead when you already know the title or author'). This is exactly the when/when-not guidance the dimension asks for, and no inference is required from the agent.

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