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

Despite annotations being sparse (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), the description fully carries the behavioral burden: it discloses cost in AI credits, latency (minutes), immediate return of scanId, the need to poll with get_ai_visibility, and the hourly rate limit. No annotation contradiction exists.

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?

Every sentence earns its place: it front-loads the core action, then covers cost, latency, return value, polling alternative, and rate limit. The description is dense but not bloated, and it is well structured with clear separations of concerns.

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?

Given the tool's complexity, the description covers all essentials an agent needs to invoke it correctly: what it does, what it costs, how long it takes, what it returns, how to retrieve results, and operational limits. The output schema exists, so return-value details beyond scanId are not required in the description.

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 the baseline is 3. The description adds meaningful context beyond the schema by clarifying that omitting domain scans the user's own site and providing a domain scans a competitor instead. This materially enriches the domain parameter's semantics, though user_intent remains only explained by 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 uses a specific verb ('Start') and a precise resource ('FRESH AI-search visibility scan'), explains what the scan does (queries live AI engines with buyer-intent prompts and checks brand visibility), and implicitly distinguishes itself from the sibling get_ai_visibility by noting it returns a scanId for later polling. This is strong, differentiated purpose clarity.

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 gives explicit when-to-use guidance: check get_ai_visibility first because reading an existing recent scan is free, and only run a fresh scan when needed. It also states the one-scan-per-hour limit and directs the agent to inform the user before calling. These are clear usage rules and alternatives.

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