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

Annotations declare openWorldHint=true, readOnlyHint=false, idempotentHint=false and destructiveHint=false, and the description adds real context beyond them: the 500-URL ceiling, single-site scoping, the first-call-returns-a-key-file handshake, and that omitting the key file makes the call incomplete. It stops short of describing response format or rate limiting, but the added operational detail is substantial.

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?

Three sentences, front-loaded with the action and engine scope, then the parameter constraint, then the workflow and triggers. Every clause carries information (engine list, exclusions, limits, setup steps) with no filler.

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 one-parameter, non-output-schema tool, the description covers the action, engine scope, URL limits, the two-step setup requirement with the sibling tools needed to satisfy it, and when to use it. Nothing an agent needs to invoke it correctly 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?

With one parameter at 100% schema coverage, the baseline is 3, but the description adds two constraints the schema does not express: a maximum of 500 addresses and that all addresses must belong to one site. That materially narrows correct usage beyond the schema's example format.

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-and-resource pair ('Tell Bing ... that pages are new, changed or deleted') and explicitly delimits the audience of engines, including a notable exclusion ('not Google'). This lets an agent tell it apart from neighbouring tools like bing_submit or bing_sitemaps without opening either 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 explicit triggers ('after publishing or updating pages, fixing redirects or removing pages') and an explicit exclusion ('do not resend pages that did not change'). It also spells out the multi-step first-run workflow (key file at site root via write_file, then call again), which is unusually complete guidance.

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