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

Annotations already declare mutation (readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=true), so the safety bar is lower. The description nevertheless adds real behavioral context beyond them: the token cost (5 from the compute bucket, scaled and rounded up), refusal on over-cap requests with the estimate returned, and guidance to read agreementBefore/agreementAfter rather than loss. Minor gap: it doesn't say whether the fitted multipliers persist or are reversible.

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 purpose is front-loaded and every sentence carries information, but the prose is dense and jargon-laden, mixing rationale and constraints into long clauses. It is longer than needed for a 3-parameter tool and could be tightened without losing content.

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 it ('Read agreementBefore/agreementAfter, not the loss'), plus caps, cost, and refusal semantics. An agent has everything required to build a valid, in-budget request.

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 baseline is 3, but the description adds genuine constraint semantics: at most 16 groups, each non-empty, no transition in two groups, and the work-estimate cap formula (loss evaluations × candidate moves × realizations × horizon). These are usage rules the schema fields do not encode.

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?

States a specific verb and resource ('Distill exact search into the play scorer: fit rate multipliers for named transition groups') with the goal condition ('so play's rankings agree with exact minimax'). It explicitly names the sibling it is not (sim_calibrate) and the axis that separates them, so an agent can route without opening schemas.

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?

Provides explicit when-to-use via the counterpart framing ('This is TACTICAL calibration — the counterpart of sim_calibrate, which learns rates from an event log') and the deliberate division of labor. It even tells the agent how to interpret a null result ('Zero agreement improvement is a finding about the structure, not a failed fit').

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