get-excluded-pages

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

Adds substantial context beyond annotations: data is built from REMOVED_FROM_SEARCH events, not a live index snapshot; deduplication is per URL with latest event winning and spans only one call; pages that returned are listed separately under returned_to_search; window bounds and max_requests cap behavior; retries not counted; and the need to pass returned_urls when continuing with offset. Annotations already cover read-only/idempotent/non-destructive, but the description carries crucial operational behavior.

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 core definition before diving into caveats, and most sentences earn their place by explaining non-obvious data semantics. It is long but justified for a tool with several tricky behaviors, though minor repetition (deduplication explained twice) and heavy capitalization keep it from being perfectly tight.

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 no output schema, the description still describes return shape sufficiently: url + excluded_url_status, bad_http_status, target_url, returned_to_search, and next_offset/exhausted for continuation. It covers all complexity around event-stream walking, pagination, and result interpretation, leaving no significant gaps.

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 100%, so the schema already documents all five parameters, including limit (excluded pages), max_requests (page fetch cap), offset, host_id, and returned_urls continuation semantics. The description largely reinforces these meanings rather than adding new parameter-level syntax or constraints beyond what the schema provides, so baseline 3 is appropriate.

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+resource: pages dropped from search inside a time window, with reasons. Explicitly distinguishes from sibling results by saying it is not the aggregate from get-summary and not a single mixed page of events, naming get-search-events-samples as the alternative.

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 explicit when-to-use (user asks which pages dropped out of search and why inside a scanned window) and when-not-to-use, naming get-summary for aggregate excluded_pages_count and get-search-events-samples for a single mixed page of events. No inference required.

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