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

Beyond the annotations, the description discloses important behavioral nuance: it is one route with two methods, action=set has two distinct modes (author vs. pin), and it adds concrete validation rules such as require being a non-empty array and min_count constrained to require.length. It also clarifies what action=get evaluates. This adds substantial context beyond the idempotent/destructive hints.

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 description is dense and front-loaded with the core purpose before expanding into action-specific detail. It is longer than the average tool description, but the length is earned because the tool genuinely has two operations and nested parameter semantics. Some protocol route detail could arguably be trimmed, but it remains relevant to explaining why one tool covers two methods.

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 complex five-parameter tool with a nested object and no output schema, the description covers most invocation concerns: action semantics, pinning vs authoring, validation constraints, and what get evaluates. It does not describe the response shape or error behavior, which would have made it fully complete given the absence of an output schema, but the core usage is well specified.

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?

Although schema coverage is 100%, the description adds meaning beyond the schema by explaining the behavioral difference between providing and omitting definition, the pinning workflow, the version-ignored-when-pinning rule, and the validation constraints on definition fields. This goes well above the baseline 3 for fully covered schemas.

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?

The description opens with a specific verb and resource: 'Read or author a task's evidence policy.' It then separates the two operations into action=get (evaluate) and action=set (author/pin), which distinguishes this combined read/write tool from the many sibling get/update tools. This is far from a tautology and gives an agent a precise mental model.

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?

The description clearly explains when each action applies: use action=get to evaluate the pinned policy; use action=set to author/update or pin. It also gives conditional guidance for definition omission versus provision. It does not explicitly name sibling alternatives or exclusions, but the dual-action structure makes the intended usage contexts clear.

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