Draft risk summary

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

The description discloses important behaviors beyond the annotations: it stores an AI note (a side effect), depends on client sampling support, and produces only a draft that should not be treated as a decision. These details meaningfully augment the all-false 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?

The description is compact and front-loaded: the first sentence states the action, the second gives a prerequisite, and the third clarifies the appropriate use. Every sentence adds value without redundancy.

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 one fully documented parameter, an output schema, and a description covering purpose, side effect, prerequisite, and limitation, the tool is nearly complete. It could be slightly stronger by explicitly noting what to do if the client lacks sampling support, but no critical information is missing.

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%, and the dossier_id parameter is already well documented with its origin and an example. The tool description adds no additional parameter-specific meaning, so the baseline of 3 is appropriate.

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 names a specific verb and resource: 'Ask the client's own model for a first-draft risk summary and store it as an AI note.' This clearly distinguishes it from generic sibling tools like add_note or get_dossier by describing a unique AI-assisted workflow.

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 clear context and a prerequisite: 'Requires a client that supports sampling,' and frames the output as 'a starting point for the analyst, never a decision.' It does not explicitly name alternatives, but the context is sufficient to guide appropriate use.

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