crawl_status

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

There are no annotations, so the description carries the disclosure burden. 'So far' does convey that results may be incremental and that polling may need to be repeated, and it lists the returned progress data. However, it does not describe error cases, status value vocabulary, or how the output evolves between polls.

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 entire description is one dense, front-loaded sentence. It names the action, the resource, and the expected output fields with no filler or repetition.

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-only poll with high schema coverage and no output schema, the description covers purpose and the main return fields adequately. It falls slightly short by not giving exact output field names for the pages fetched or the possible status values, but it is still sufficient for an agent to call the tool correctly.

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 coverage is 100% and jobId is already documented as 'The id returned by crawl', which orients the agent well. The description adds no additional parameter meaning 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?

The description opens with a specific verb and resource: 'Poll a crawl job', and it names the key monitored fields (status, pagesCrawled, pagesQueued, pages fetched). It is clear, but it does not explicitly differentiate from sibling tools such as collector_run_status.

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 verb 'Poll' implies the tool is used after starting a crawl and to monitor progress, but the description never explicitly states when to use it instead of alternatives, nor does it mention any exclusions or related tools like crawl or collector_run_status.

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