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

Annotations cover safety (readOnly=false, destructive=true, openWorld=true) but the description adds genuinely non-redundant behavior: async execution, the 30-90s wait, credit consumption on the START call only, free task_id fetches, and where to top up. This is exactly the extra context annotations cannot express.

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 one-line purpose, then the workflow in call order, then cost. Dense but almost every clause carries a fact the agent needs; the long parenthetical issue list is slightly heavy but useful.

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 an output schema present it correctly avoids restating return shapes, yet still names what the summary contains (pages crawled, scores, issue counts, broken_link_sources). Complete for the workflow; the only gap is the unaddressed refresh/max_pages semantics.

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 0%, so the description carries the param burden — and it does explain the three most important ones: task_id (start vs fetch mode), issue (paged full-URL drill-down), and limit/offset (paging). It leaves refresh and max_pages undocumented, so it compensates well but not completely.

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+resource ('Site-WIDE technical crawl') and immediately scopes it against the obvious alternative class ('not a single page'), which separates it from single-URL siblings like instant_audit. The async two-phase nature is stated up front so the agent knows what it is invoking.

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?

Explicitly says when to use it ('when the user wants a whole-site audit, not just one URL') and then walks through the exact call sequence: start without task_id, re-call with task_id after ~30-90s, then re-call with issue for full URL lists. Nothing about invocation order is left to inference.

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