policy_evaluate

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so 'without changing reports' is largely redundant with structured data. The description does add domain context by naming the three classes of policy checks performed (thresholds, coverage requirements, expiring waivers), which goes slightly beyond the annotations, but says nothing about required inputs, permission needs, or failure behavior.

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 front-loaded sentence with no filler or repetition, and the non-mutating constraint is placed at the end where it reads naturally. It is efficient, though the packed enumeration of policy check types makes the sentence dense without adding usable operational detail.

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?

An output schema exists so return values need not be explained, but the tool has three parameters at 0% schema coverage and no usage guidance, so an agent cannot reliably construct a call — particularly the required policy_path. The description is too thin for a parameterized evaluation tool.

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% for three parameters, so the description carries the full burden and fails to meet it. It never mentions policy_path (the sole required parameter), report_id, or baseline_id, leaving format, expected values, and the meaning of 'latest'/null defaults entirely undocumented.

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 (evaluate) and enumerates the policy objects being checked (team thresholds, explicit coverage requirements, expiring waivers), which tells an agent this is a policy-compliance evaluation rather than a report mutation. However, it never distinguishes itself from plausible siblings like reports_compare or audit_scan, so the agent must infer where it fits.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. The only directional signal is the trailing phrase 'without changing reports', which implies a read-only, non-mutating context but does not say when this should be preferred over reports_compare or dependency_check.

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