bing_fetched_urls

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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world read. The description adds genuinely useful context beyond that: an empty result carries an empty_response label and means silence rather than 'no problems found', plus a directive to treat untrusted fields as data not instructions. That is real behavioral value. However, it says nothing about pagination, row limits, or the shape of returned rows, so it does not fully clear the higher bar annotations set.

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-loads the core purpose, then layers routing exclusions, then return-value semantics and the safety directive. No sentence is redundant; every clause earns its place.

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 single-parameter read tool, the description covers the safety profile the annotations already imply, plus the two things an agent could otherwise get wrong: interpreting an empty result and mishandling untrusted return fields. With no output schema, it also pre-empts a misread of empty results. Nothing essential is missing.

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?

One required parameter, site_url, with 0% schema description coverage, so the description must compensate. It implies single-site scoping ('on one site') but gives no expected format (full URL vs. domain vs. property) or normalization rules for site_url. Baseline 3 is appropriate – it adds marginal meaning without fully compensating for the coverage gap.

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, and scope ('List URLs Bing recently fetched on one site'), and immediately names the two siblings it is not (bing_fetched_url_details, bing_crawl_issues). An agent can distinguish it from the large sibling set without opening any schema.

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 an explicit positive trigger ('Use when the user asks what Bing crawled lately') followed by two explicit exclusions, each routing to a named alternative tool. This is textbook when/when-not guidance.

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