Search the catalogue

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive nature, but the description adds valuable behavioral context: matching occurs on titles, creators, and descriptions (not content), media types can mix and require narrowing, and each row carries an identifier usable with get_item. These are non-obvious traits beyond the structured annotations.

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?

The description is compact yet information-dense. Every sentence contributes: scope, matching behavior, content-search exclusion, media_type advice, and identifier output. It is front-loaded with the primary action and resource, and no sentence is redundant.

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?

Given the 7 parameters and presence of an output schema, the description covers the essential context: what is searched, how results should be interpreted, when to use alternatives, and a concrete hint about the persisted identifier. With the output schema providing return field details, this description is sufficient for an agent to select and invoke the tool correctly.

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?

The schema covers 71% of parameters with descriptions, and the description adds operational meaning: it explains why media_type should be set for readability, clarifies the matching scope of the query, and notes that sort='downloads' can surface popular items. This compensates for the missing schema descriptions and adds decision-useful semantics.

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 starts with a specific verb and resource: 'Search the Internet Archive catalogue' and enumerates the media types covered. It distinguishes itself from siblings by explicitly mentioning search_inside and get_item, clarifying what this tool does not do (content search) and what it offers (identifier for later retrieval).

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?

Explicit guidance is given: use search_inside for phrase-within-a-book searches, set media_type when the kind is known, and note that a compilation can rank alongside a person's own work. This clearly tells the agent when this tool is appropriate and when to choose an alternative.

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