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

Annotations already declare readOnlyHint=true, so the trailing 'Read-only' is redundant restatement. What does add value beyond the annotation is the disclosure of returned fields, including permission flags can_decide and can_run, which tell the agent whether follow-up actions like approve/execute are available; it does not cover errors for unknown or unauthorized ids.

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?

A single sentence, front-loaded correctly with 'One cost decision', but it is overloaded with a backticked CLI reference that gives an agent no actionable value and with the opaque phrase 'settled against the operation that runs it', which spends words without conveying meaning.

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 required param, no output schema, and read-only annotations, the description is nearly sufficient: it enumerates the fields the agent will get back, which substitutes for a missing output schema. The remaining gap is how to obtain a valid decision_id and what happens on an invalid or unauthorized one.

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 schema already explains decision_id originates from list_cost_decisions, so the description adds nothing about parameters. Baseline 3 applies since the structured field does the work.

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?

Names a specific verb+resource (fetch one cost decision) and enumerates what it carries (plan, plan_hash, evidence, status, run receipt, measured saving, can_decide/can_run), which distinguishes it from list_cost_decisions. The CLI-parity parenthetical and the vague clause 'settled against the operation that runs it' blur rather than sharpen the purpose.

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?

No explicit when-to-use or when-not guidance, and no alternative is named even though list_cost_decisions and execute_cost_decision sit right next to it in the tool set. The only implicit signal is that it takes a single id, leaving the agent to infer that listing comes first.

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