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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral facts: the tool grades rather than computes, it has a built-in synthetic fallback when request is omitted, and 'this does not verify a licence' honestly disclaims the rights_confirmed flag. That last caveat is exactly the kind of nuance annotations cannot express.

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 sentences, zero filler, and the core action is front-loaded before the fallback and permission caveats. Each sentence adds a distinct fact the caller needs.

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?

Output schema exists, so return values need not be described. However, the input is a six-required-field nested request with a limits array of up to 1000 entries, and the description never indicates what the grading produces per limit (pass/breach, warning thresholds) or how results keys map to metrics. Adequate for the top-level routing decision, thin for correct payload construction.

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%, so the description must carry the load, and it does explain the two top-level parameters meaningfully: omitting request selects synthetic data, and rights_confirmed is a permission attestation. It says nothing about the inner LimitRequest payload (limits, results keys, data_mode interaction with synthetic vs user-licensed), leaving the most complex part to bare schema titles and enums. Partial compensation warrants a 3.

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: 'Grade a limit set against exposure, tail and stress results'. The phrase 'already returned by Risk Desk' scopes it as a post-processing/verdict tool, which reads distinctly from computation siblings like risk_exposure or risk_stress. It stops short of naming a sibling it could be confused with, so it does not reach 5.

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?

'Omit the request to run the shipped synthetic example instead' is an explicit branch condition, and 'For supplied data, require permission and set rights_confirmed=true' states a precondition that gates the user-data path. Both are clear when-to-use signals. No alternative tool or when-not-to-use guidance is offered, so it is short of 5.

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