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

Annotations already declare readOnlyHint, idempotentHint, closed-world and non-destructive, so safety is covered; the description adds real behavioral context beyond that — results are presented as cards, difficulty is a 0-100 composite of nine prose/meaning dimensions, and results carry no indication of whether the user has read the book. It stops short of describing ordering, empty-result behavior, or what happens when limit exceeds the catalog, leaving minor gaps.

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 purpose, then usage routing, then returns, then examples — a clean progression with no filler sentences. The explicit 'Returns:' enumeration is partly redundant given an output schema exists, which keeps it off a 5.

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 7-parameter, zero-required search tool with an output schema, the description supplies everything needed to call it correctly, including the read-history caveat that prevents a wrong inference from results. The only room left is behavioral detail on ordering and pagination past the 50-item cap.

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 four worked examples demonstrate how parameters combine (query + genres + a difficulty band, and genre-only with difficulty_max), which the schema cannot express. The Russian example also clarifies the cross-cutting rule that localized fields are added while difficulty scores stay language-independent, going beyond the schema's note about Cyrillic auto-detection.

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 (searches) plus the resource (ReadingRate book catalog) and enumerates the searchable facets (title, author, genre, theme, difficulty). It also names the concrete output shape (book cards with a 0-100 difficulty score built from nine dimensions), so an agent can distinguish it from content search, award lookups, and batch lookups without opening a 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?

Gives an explicit when-to-use clause ('asks to find books by an author, on a subject, in a genre, or within a difficulty range') and then routes four alternatives by condition: get_book_details for one book's analysis, get_award_winners for prizes, lookup_books_batch for pasted lists or photographed shelves, get_reading_history for read status. This is the full when/when-not/alternatives pattern.

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