company_inference_cost

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

With no annotations provided, the description carries the full burden of disclosing side effects. It explicitly states 'moves no money', which is a clear behavioral note about the tool's non-financial impact. The phrase 'Returns a report' also sets expectations about the output.

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 extremely concise and well-structured, consisting of just two sentences. It packs the core purpose and a key behavioral note into a minimal number of words without any 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?

While the description explains what the tool does and that it returns a report, it lacks context about the nature of the JSON inputs and the report structure. An agent would need more domain knowledge to understand 'retained inference cost sources' and how the parameters relate. The output schema is not provided, so the 'report' is vague.

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?

The schema has no descriptions for any parameters, and the tool description does not explain the meaning or expected format of inputs like bundle_json, metered_json, or statement_json. Even common fields like project_id are left unexplained. This makes it very difficult for an agent to construct a valid request.

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 clearly states the tool's function: reconciling retained inference cost sources for a matching company bundle. The verb 'Reconcile' and the specific object 'retained inference cost sources' give a precise purpose. The additional note 'Returns a report; moves no money' further clarifies the expected output and non-financial nature.

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 does not provide any guidance on when to use this tool over other company_* tools. It lacks context about scenarios where reconciliation is needed or how it fits into a larger workflow. There is no mention of alternatives or preconditions.

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