Usage and models

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

Annotations already cover readOnly/idempotent/openWorld/non-destructive. The description adds beyond them: it discloses that the call is 'Free' (no budget consumption) and that the models flag expands the response, which is genuinely useful behavioral context. It does not cover rate limits or response size, keeping it out of 5 territory.

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?

Two compact sentences with the return data front-loaded ahead of the usage tip; nothing is wasted. The telegraphic phrasing ('models: true') is efficient if slightly clipped.

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 by naming the key figures returned. Combined with 100% parameter coverage and clear annotations, an agent has everything needed to call it 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 100%, so the schema already documents both parameters fully. 'models: true adds the model table' restates what the schema description ('Add the model table per alias') already says, and the candidates object is left entirely to the schema. Baseline 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 enumerates exactly what the tool returns (today/all-time spend, budget left, OpenRouter key limit, optional model table), so the resource is precisely defined. It stops short of a clean verb-phrase opening, but an agent can confidently tell this is the usage/cost reporting tool versus eyes_run and eyes_result.

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?

It gives an explicit trigger: check before a large job or when eyes_run hits the budget, naming the sibling that precedes it. No when-not or alternative-stats-tool guidance, but the usage context is unambiguous.

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