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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by stating the scope (40M+ items), the mediatype filters, and the specific fields returned, which are not in the annotations. It also mentions the underlying advancedsearch.php, providing implementation context. There is no contradiction. The description does not cover pagination or rate limits, but with annotations handling the read-only nature, this is sufficient.

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 a single, front-loaded sentence that immediately states the action and scope. It packs in mediatype categories, filters, and return fields without any fluff. The parenthetical at the end names the underlying API, which is a minor but useful detail. Every clause earns its place; no redundant information or padding.

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 availability of an output schema (which is noted as present) and the annotations covering read-only/idempotent behavior, the description is complete for an agent to correctly invoke the tool. It covers what is searched, how to filter, and what is returned. Pagination details are left to the input schema (page, rows), which is acceptable. The description provides enough context to select this tool over siblings and to formulate a correct query.

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 has 100% coverage with descriptions for all 5 parameters, so the baseline is 3. The description adds extra value by explicitly listing the mediatype options and including a usage hint: 'Omit to browse by mediatype/creator alone' when query is not provided. This goes beyond the schema's individual descriptions. It also clarifies what fields are returned, though that's output semantics. Overall, it enhances parameter guidance beyond the 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?

The description clearly states the tool's purpose: searching 40M+ items in the Internet Archive across multiple mediatypes. It lists specific filters (mediatype, creator) and return fields (identifier, title, creator, date, description), distinguishing it from sibling tools like archive.metadata (which would retrieve metadata for a specific item) and wayback.check_availability (which checks URL availability). The verb 'search' plus the resource and scope makes the purpose unambiguous.

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?

The description gives clear context for when to use this tool: when searching across the archive. It mentions how to filter by mediatype and creator, and implies that omitting query allows browsing. However, it does not explicitly mention when not to use it or recommend alternatives (e.g., for metadata of a specific identifier, use archive.metadata). This falls short of explicit when-not/alternatives guidance, but the core usage context is well defined, warranting a 4 rather than a 5.

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