run_scan

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

No annotations are provided, so the description carries full disclosure burden. It explicitly discloses that it's a WRITE ACTION, consumes one scan from quota, adds tracked brands to brand cap, may replay a shared measurement, and adds no entry to list_audits in the replay case. This is exemplary transparency for a resource-consuming mutation tool.

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 dense and informative, front-loaded with purpose then caveats then alternatives then plan requirements. Every sentence carries distinct information with no filler. Slightly longer than strictly necessary but every clause earns its place given the multiple behavioral caveats needing disclosure.

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 write action with no output schema and no annotations, the description covers purpose, quota/brand implications, replay behavior, when-not-to-use, plan tier requirements, and param-level nuance. Despite no output schema, the description mentions the returned result shape (scores, citation matrix, competitors, top gaps), making this highly complete for the complexity involved.

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 both url and competitors have adequate schema docs. The description adds moderate value beyond schema: it clarifies url accepts bare domain or full URL, states competitors count limit (up to 8), and notes that passing competitors forces a fresh run. This exceeds baseline 3 slightly but the schema already handles param details.

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 verb+resource (Run an AI-visibility audit) and specifies the output (scores, citation matrix, competitors, top gaps). It distinguishes this from sibling tools by naming get_audit/list_audits as read alternatives for existing audits, situating run_scan as the fresh-data option.

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 guidance on when to use vs alternatives: 'Prefer list_audits/get_audit to read an existing audit for free; use run_scan only when fresh data is needed.' Also explains caveats (7-day replay for untracked domains, brand-cap impact) and plan-tier requirements (Pro or higher, read-only on Starter/trial) that tell the agent when this tool is not usable.

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