Check Control Gaps

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

With no annotations provided, the description carries the full burden, and it does so well: it explicitly states the tool is read-only, does not mutate the model, runs as a polled background job, and uses LLM reasoning. These are meaningful behavioral traits beyond what the schema alone reveals.

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 compact and front-loaded: the first sentence states the core purpose, the second covers behavior, and the final paragraph distinguishes the tool from its sibling. No sentence is wasted.

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 description covers purpose, behavior, async execution, and the key alternative, and an output schema exists to cover return values. The main gap is the unexplained server_version parameter, and the description does not mention how to obtain or poll the background job's result.

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 only 50%: model_id has a description but server_version does not. The description adds no parameter-level guidance at all, leaving server_version's meaning and format unexplained. It does not compensate for the low schema coverage.

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 specific verbs ('Analyze', 'surface') tied to a clear resource: control coverage and control objectives lacking sufficient controls. It also explicitly differentiates itself from assess_model, making its purpose unmistakable.

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 guidance: used to decide what controls to add, while assess_model is used to score the current state. It also contrasts its LLM-based reasoning with assess_model's deterministic computation, so an agent can choose correctly between the two.

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