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

Annotations already indicate read-only, open-world, idempotent, non-destructive behavior. The description adds meaningful behavioral context on top: it consumes a shared daily paid budget, can return quota_reached with UTC reset time, uses up to five prompts, and returns cached completions without polling. No contradiction with annotations.

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?

Purpose is front-loaded, followed by three distinct operational facts (cost/quota, polling sequence, caching) with no filler. The longer length is justified by the async paid behavior that the agent must understand before calling.

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?

There is no output schema, yet the description covers the necessary runtime contract: result can be running or quota_reached with reset time, pollAfterSeconds, runId, and caching behavior. An agent has enough to invoke and follow through correctly.

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 80%, and the description adds no per-parameter information beyond what the schema already documents; it only references runId/pollAfterSeconds as part of the response workflow, not input semantics. Baseline 3 is appropriate when the schema carries most parameter meaning.

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 action ('Start an AI visibility check') and defines the domain question: whether the business appears in AI assistant local-provider answers. It references get_audit_report, making its role as the start-side counterpart clear and distinguishing it from polling/audit siblings.

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?

Provides an explicit polling workflow: wait pollAfterSeconds, call get_audit_report with runId, repeat while running, and skip polling for cached results. It doesn't explicitly say 'use this instead of X,' but the workflow and budget/quota caveat tell the agent when and how to invoke it.

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