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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower. The description adds real behavioral context the annotations cannot: results are personalized for linked accounts, exclude books already in the library or hidden/avoided/passed-on, and include a rationale when a result fits the reader's taste.

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 core purpose and the illustrative examples are front-loaded in a single dense sentence, with personalization behavior following. It is longer than most descriptions but nearly every clause carries information; the only slack is the extended list of exclusion categories.

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 usefully sketches what comes back (personalized, filtered results with an explanation when taste matches) and how input is interpreted. The missing piece is semantics for limit/isFiction, which the description never touches despite low schema coverage.

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 description coverage is only 33%, so the description must compensate. It enriches the 'description' parameter well by characterizing it as free-form mood/theme/subject language, but says nothing about 'limit' or 'isFiction', leaving two of three parameters undocumented anywhere. Adequate but with a clear gap.

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 (book recommendations) and explicitly delimits the matching mode: 'Matches on meaning rather than on a title or an author name.' This distinguishes it cleanly from recommend_from_titles without the agent needing to open either 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 queries ('cozy fantasy with found family', 'a good book about grief') show the intended input shape, and the semantic-vs-title contrast implies when to pick this over a title lookup. It stops short of naming the sibling recommend_from_titles as the explicit alternative, so the routing is clear but not fully spelled out.

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