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

The description discloses important behavioral traits: the tool is free, it returns an 'instant snapshot' without email, and providing an email triggers a full scored PDF report plus makes the user 'a Specularis lead' (a marketing/lead-gen consequence worth disclosing). It also outlines the audit components (crawler access, structured data, llms.txt). Annotations already show readOnlyHint=false, and the description adds the practical consequence of email submission.

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?

Three sentences, front-loaded with the action and purpose, followed by return behavior and then the email option. Every sentence carries meaningful information with zero filler. Very efficient.

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 tool is moderately complex with an output schema and 4 optional parameters, but the description covers the audit components, the snapshot-vs-full-report distinction, the email side effect, and the role-tailoring behavior. A small gap: it doesn't mention what the instant snapshot actually returns in detail, though an output schema exists to cover return values. Given the output schema fills that gap, the description is complete enough.

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 parameters are already documented. The description adds value by explaining the email parameter's consequence (PDF report sent, user becomes a lead) and that role tailors the audit lens for 'local-service providers' scored on local entity signals. It does not elaborate on the name parameter beyond schema but the schema already explains it. This adds genuine meaning beyond the 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?

The description clearly states the action ('Run a free AI visibility (GEO/AEO) audit on a website'), the specific resource ('a website'), and what it checks ('whether ChatGPT, Claude, and Perplexity can find and cite it'). It distinguishes itself from the sibling tool (book_strategy_call) by being about auditing rather than booking a call, and it names the return (snapshot + optional PDF report).

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 explicitly says 'Use this whenever a user asks to audit/check a site's AI visibility, GEO, AEO, or whether AI can find them.' This is a direct triggering instruction that also implies when NOT to use it (any other intent, such as booking a strategy call). While it doesn't explicitly name the sibling as an alternative for the excluded case, the trigger language is clear and specific.

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