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

Annotations already declare destructiveHint=true, openWorldHint=true, and readOnlyHint=false, but the description adds no further behavioral context. It does not disclose side effects like consuming an audit credit, the asynchronous nature of the audit, or that it actively scans the target site. Given the annotations are present, the description's failure to elaborate on these traits leaves a notable gap.

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 description is a single sentence that efficiently front-loads the core purpose ('Achilles 10-stage audit for a website') before listing outputs. It is not overly verbose, though the list is long. It could be broken into two sentences for readability, but it is acceptable.

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?

The output schema likely covers return structure, so the description's list of return values is somewhat redundant. However, it lacks important process context: that the audit is asynchronous, that it may consume credits (implied by email param), and that progress can be tracked via ghost_audit_status. These omissions leave an agent uncertain about the full call flow.

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%, and both parameters have descriptive text (url with example, email with note about passes). The tool description does not add any parameter-level meaning beyond the schema, so it neither helps nor hinders. A baseline of 3 is appropriate.

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?

The description states a specific verb ('audit') and resource ('a website'), and lists concrete outputs (SEO gaps, AI discoverability, conversion leaks, etc.) that clearly distinguish it from sibling tools like ghost_audit_report (which likely retrieves a completed report) and ghost_audit_status (which tracks progress). The 'Achilles 10-stage' phrase adds specificity.

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 implies this tool initiates a new audit by listing the returned audit ID and live stream URL, but it does not explicitly compare against alternatives. It does not state 'Use this to start an audit; use ghost_audit_status to check progress' or mention when to use provibe_audit instead. Guidance is only implicit.

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