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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety bar is lower. The description still adds real behavioral context beyond them: it resumes from a saved frontier (explaining the non-idempotent resume semantics) and consumes additional page budget. It does not clarify why the operation is flagged destructive, which is the remaining gap.

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?

Two tight sentences: the precondition and core action are front-loaded, and the trailing sentence is an actionable next step rather than filler. 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?

With no output schema, the description compensates by telling the agent to poll get_crawl_status for results. For a 2-parameter mutation tool, precondition, action, and post-action are all covered.

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% – both job_id and additional_pages (including the 500 default and plan-cap note) are fully documented in the schema. The description only alludes to the page limit, adding no syntax or semantics beyond the schema, so the baseline of 3 applies.

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?

Specific verb (extend/resume) applied to a specific resource (a crawl), with the exact state precondition (status "partial", coverage.reason "page_limit_reached"). This cleanly distinguishes it from start_crawl (new crawls) and get_crawl_status (read-only polling).

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 a precise when-to-use condition via the status/reason pair and names the follow-up tool (get_crawl_status). It stops short of an explicit when-not-to-use (e.g., 'for new crawls use start_crawl', or behavior on failed crawls), so it is strong but not fully closed-loop.

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