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

Annotations already cover read-only/idempotent/non-destructive, so the bar is lower; the description still adds non-obvious context: free of charge, deterministic, that the policy is supplied by the caller rather than looked up, and that unknown targets trigger review. The verdict's return shape remains undisclosed, keeping it short of a 5.

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?

Three tight clauses with the defining attributes ('Free', 'Deterministic', 'read-only') front-loaded and no filler. It is efficient, though the extreme terseness leaves required detail unstated rather than merely being concise.

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?

For a policy-verdict tool with no output schema and an undocumented 8-field request object, the description omits what a verdict looks like and how the numeric-ceiling fields interact. Annotations carry the safety profile, but the request contract is under-specified for the tool's complexity.

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 0% with a nested 8-field request object, so the description must compensate. It maps concepts to fields ('amount', 'destination', 'approval ceiling', caller-supplied 'policy'), which helps, but does not name or disambiguate the actual fields (spend_usd, approval_usd vs max_approval_usd, unlimited_approval, allowed/blocked_targets).

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?

Specific verb-phrase ('deterministic read-only spend policy verdict') tied to concrete inputs (amount, destination, approval ceiling), so the core job is legible. It does not, however, distinguish itself from close siblings like allowance_risk_check or tx_preflight, leaving the agent to infer the boundary.

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?

'Caller supplies policy; unknown targets require review' gives real context about invocation and one behavioral rule. But there is no explicit when-to-use/when-not guidance and no routing to the most similar siblings (allowance_risk_check, tx_preflight), so usage is only implied.

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