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

Goes well beyond the readOnly/openWorld/idempotent annotations by describing multilingual embedding behavior, evidence grouping, language/status/source/coverage identification, and important caveats about catalog descriptions and thematic absence. This gives the agent realistic expectations about result semantics.

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?

Compact and information-dense with no filler. Key facts about multilingual search, result grouping, lexical queries, and limitations are all included in a short description that front-loads the main purpose.

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 tool with a large filter schema and no output schema, the description provides useful return-shape details, multilingual semantics, and open-world limitations. It does not explain filters, pagination, or explicit sibling routing, but the annotations and schema fill some of that gap.

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 0%, so the description carries the burden. It explains query language flexibility and lexicalQueries BM25 terms, but says nothing about the extensive filters object or the limit parameter. This is partial compensation for an otherwise undocumented schema.

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 action: searching public catalog metadata and passages with multilingual embeddings, with results grouped by bibliographic work. This clearly distinguishes it from broader listing tools and from the title alone.

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?

Provides clear context that queries may be in any language, explains optional lexicalQueries, and notes that listing tools provide exhaustive bibliographies. It does not explicitly name or contrast the closest sibling, search_publication_text, but gives enough context for many cases.

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