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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds the high-value context those annotations cannot express: credit consumption, asynchronous execution with an immediate audit_id return, multi-minute latency, the polling contract, and 24h cache behavior. This is exactly the behavioral context an agent needs to sequence calls.

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?

Four sentences, each carrying distinct, non-redundant information: purpose, cost, async contract, and caching. The most decision-critical facts (cost, return shape) are front-loaded ahead of the polling instructions.

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?

With no output schema, the description carries the return-value burden and does so: it names the returned audit_id, explains job_status polling, and directs the agent to detail 'summary' then 'full'. Combined with 100% schema coverage, an agent has everything needed to call and follow up 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 description coverage is 100%, so every parameter is already documented in the schema and the baseline is 3. The description adds no parameter-level detail beyond what the schema provides (the competitor benchmarking mention maps to the existing 'competitors' param).

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?

Opens with a specific verb+resource ('Start an AI Visibility Audit') and immediately scopes it: measures brand visibility in AI assistant answers across a query set, with competitor benchmarking. This is clearly distinguishable from siblings like get_brand_audit, get_brand_trend, and list_brand_audits.

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?

Explicitly states the cost ('Costs 1 audit credit'), that it is asynchronous, and gives the exact follow-up workflow: poll get_brand_audit with detail 'summary' until job_status is 'completed', then fetch detail 'full'. It also names the caching condition (identical requests within 24h). No inference required.

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