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

Annotations already declare read-only, idempotent, non-destructive behavior, so safety is covered. The description adds real behavioral context beyond that: keyword is conjunctive across title + abstract, metadata/filter values use French labels, results truncate abstracts to a snippet, and the corpus is multilingual. Missing only rate/limit behavior (limit is left to the schema).

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 verb and resource, then progressively more operational detail. Every sentence carries information (matching semantics, multilingual advice, result truncation, next-step tool), though the density of parenthetical hints makes it slightly cramped.

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 10-parameter, no-required-parameter search tool with no output schema, the description covers the matching model, language pitfalls, result shape (snippet), and the follow-up tool for full records. Pagination defaults and the sparse subject tag live in the schema, so the remaining gaps are minor.

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 80% schema coverage the baseline is 3, and the description earns above that by clarifying the AND semantics of keyword, the quoting convention for phrases, and the important non-obvious fact that reference_type and language take French labels. It doesn't restate the country/date filters, which the schema already documents well.

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 (search) and resource (academic references) and enumerates the resource types covered (journal articles, book chapters, theses, books, reports). It clearly delimits the search mechanism to keyword matching on title + abstract, which separates it from the many get_* siblings, though it does not explicitly name search_articles or semantic_search_references as the alternatives.

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 concrete directional guidance: try French and English keywords when relevant, use 'quote' for phrases, and use get_reference instead when the full abstract or bibliographic detail is needed. Clear usage context, but it never states when to prefer this over semantic_search_references or search_articles, so the sibling routing is incomplete.

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