Search chapters, topics and objectives

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

Annotations already declare readOnly, idempotent and closed-world, so the safety bar is lower. The description adds real context beyond them: the searchable fields, that hits are small and carry IDs and page numbers, and the non-obvious behavior that query language determines which book version is searched by default. It does not mention empty-result behavior or pagination, which keeps it from a 5.

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 tightly packed sentences, front-loaded with purpose and examples, then search scope plus return shape plus handoff, then the version nuance. The bilingual example strings earn their length by demonstrating the query format directly. No filler or restated field names.

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 carries the return-shape burden and does so (small hits with IDs and pages). It covers scope, bilingual behavior, follow-up routing, and version defaults, and the remaining details (limit, subject defaults) live fully in the schema. Nothing an agent needs in order to call it correctly is missing.

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 100%, so the baseline is 3, but the description genuinely adds meaning the schema cannot: the interaction between query language and the version parameter's effective default. The bilingual query examples also clarify what the query parameter accepts in practice. The limit and subject defaults are left to the schema, which is fine.

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?

The description gives a specific verb and scope: "Find where a concept is taught," then enumerates exactly what is searched (chapter titles, section headings, learning objectives). It also names what it returns (small hits with IDs and pages) and routes detail lookups to get_topic, so an agent can distinguish it from list_chapters and get_objectives without opening schemas.

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 states the use case clearly (locating where a concept is taught) and gives an explicit follow-up path: "call get_topic on an ID for details." It also explains the version defaulting rule with a conditional ("unless version is set"). It stops short of stating when NOT to use it (e.g., browsing all chapters, which is what list_chapters is for), so it is clear but not fully exclusionary.

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