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

Annotations mark this as a non-readonly, non-idempotent, open-world operation, and the description is consistent, adding that it returns an audit_id and that a new audit should only be started after searching for existing work (a de-facto duplicate-work warning). It does not state auth requirements beyond 'follow the user's permission' or what state the audit creates.

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?

Short, front-loaded sentences with zero filler, and the purpose leads. Some clauses ('follow the user's permission', 'Pass campaign context already supplied') are terse to the point of ambiguity, slightly reducing clarity.

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?

Covers purpose, the downstream workflow (audit_id → get_audit → run_cro_skill), a negative scope statement, and the search-first precondition, which is sufficient given no output schema. Auth/permission mechanics remain vague.

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%, so both url and context are already documented in detail. The description's 'Pass campaign context already supplied' merely restates the schema's guidance to pass what the user has already said, adding no syntax or format detail beyond the schema baseline.

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 ('Start a new landing page audit') and explicitly differentiates from siblings: 'Does not design or build a page' rules out build_page, and the audit_id workflow routes to get_audit and run_cro_skill. An agent can identify this as the creation entry point without opening the schema.

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?

Explicit routing: use check_balance for page coverage, search for existing work when the request concerns a prior audit, then get_audit with wait:25 followed by run_cro_skill. It names the alternatives and the conditions that select them, so nothing 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.