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

Annotations already declare idempotentHint=true, readOnlyHint=false and destructiveHint=false, but the description adds concrete semantics the annotation does not: a running or queued run 'short-circuits,' so the caller learns that a second call will not spawn a duplicate job. 'Enqueue' also signals asynchronous, non-immediate execution. It does not cover rate limits, credit/cost implications, or how to observe progress.

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, zero filler, with the core action front-loaded and the idempotency caveat second. Nothing could be removed without losing information.

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 trigger tool with no output schema, the description says nothing about what the call returns (e.g., a run/job identifier) or how to follow up — get_scan_pages, get_site_audit, get_score_history are the obvious polling siblings and go unmentioned. Annotations cover the safety profile and the single required parameter is fully documented, so it is adequate but leaves a real observability gap.

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?

Only one parameter (site_id) and schema description coverage is 100%, with the schema itself stating 'UUID of the site.' The description adds 'for a site' but no format, sourcing, or validation detail 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?

States a specific verb and resource: 'Enqueue a fresh crawl + audit run for a site.' An agent can tell this triggers a scan rather than reading results, which separates it from the many get_* siblings. It stops short of naming the closest alternatives (run_public_scan, start_ranking_run), so the boundary is inferred rather than stated.

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?

Usage is implied — call this to kick off a crawl/audit for a known site — and the idempotency note hints that duplicate calls are harmless. However, there is no explicit when-to-use versus run_public_scan or start_ranking_run, and no stated prerequisites (e.g., site must already exist / be verified).

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