Build semantic index

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

Goes well beyond the annotations: discloses that large selections may outlive client timeouts and that re-running resumes because up-to-date books are skipped, explains the automatic fallback to keyword-only indexing when the embedding model is absent, and warns that prune drops orphaned index entries. This is exactly the operational context the idempotentHint alone doesn't convey and is consistent with readOnlyHint=false.

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?

Front-loaded with the required-scope constraint, then ordered by operational importance (long-running/resume, build variants, force, prune). Dense but every sentence carries behavioral information; only minor tightening would improve it.

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?

An output schema exists, so return values needn't be described, and the long-running/resume and fallback semantics are well covered for a mutating indexing job. The remaining gap is the two undocumented parameters (enableFts, library), which an agent cannot reason about from either schema or description.

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 0% schema description coverage the description carries the full load, and it explains five of eight parameters meaningfully (bookId/ids/query, keywordOnly, force, prune) including their side effects. enableFts and library are left completely unexplained, which keeps it from a 5.

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 ('Build the semantic index') and immediately scopes it ('for specific books'), which separates it from the sibling search/report tools. The added note that full-library indexing is deferred further sharpens the boundary.

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 clear when-to-use context: scope selection via bookId/ids/query, re-run after adding books, and force for re-indexing unchanged books. It does not explicitly name which sibling consumes the index (calibre_semantic_search) or when to prefer a keyword-only build over a full one beyond the embedding-model case.

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