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

Goes well past the readOnlyHint/openWorldHint annotations: discloses async behavior, crawl scope (internal links + sitemap, page cap), the exact check categories performed, that it is deterministic and uses no LLM, per-IP/per-host quotas, dedup on repeat calls, and the auth path for higher limits. This is the kind of behavioral context annotations cannot carry.

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?

Front-loaded with the action and the async return, then grouped into crawl scope, checks, and quota/auth. The check list is long but each item is concrete and useful for anticipating results; nothing 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?

For a two-param async tool with no output schema, the description covers the immediate return value (auditId), how to retrieve results, expected latency, crawl breadth, what the audit inspects, and quota/auth constraints. An agent has everything needed to call it correctly and set expectations.

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%, so the schema already documents both parameters including the 1-30 range and default 15. The description restates the range and adds the crawl semantics ('following internal links and the sitemap') and a speed tradeoff, but that is modest added meaning beyond a fully documented schema.

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 ('Starts a full technical audit of a whole website') plus the async contract ('returns immediately with an auditId'). The phrase 'whole website' implicitly separates it from the single-page sibling scan_website, and it explicitly routes to get_audit for polling, so an agent can distinguish it from siblings without opening schemas.

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 clear operational context: poll get_audit every 20-30 s, typically 1-5 min, plus rate-limit conditions and the dedup rule ('a repeat call for the same host returns the existing audit'). It does not explicitly say when to prefer this over scan_website or recheck_website, which is the one missing routing cue.

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