Start Link Check

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

Annotations only declare destructiveHint=false; the description adds substantive behavioral context beyond that: the operation is asynchronous, returns a job_id immediately, and requires polling another tool until completion. It does not disclose whether concurrent checks are allowed, whether one can be cancelled, or the cost/scope of scanning all content.

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 key facts (async, scope, immediate job_id, polling target) are packed into the first two sentences with nothing wasted. The code-block example adds concrete grounding, though it partly restates the workflow in prose, so it is slightly longer than strictly necessary.

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 zero-parameter async trigger with no output schema, the description covers exactly what an agent needs: what it does, that it returns a job_id, and which tool to call next to observe the result and how to interpret its status.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly conveys that no inputs are needed and instead documents the returned job_id, which is the only value the caller must carry forward.

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 ('Start'), resource ('broken-link check'), scope ('across all published content'), and modality ('asynchronous'). It also names the companion sibling get_link_check_results, so an agent can distinguish this trigger from the tool that reads its output.

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 description gives a clear workflow: call this to start, then poll get_link_check_results(job_id) until status is 'done', with explicit retry behavior while 'running'. It does not state when NOT to use it (e.g., overlap with run_maintenance_scan or whether a check is already in flight), so it falls short of full 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.