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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the description carries no extra safety burden. Beyond that it adds essentially nothing: no ordering of versions (newest first?), no pagination behavior, no note about what a version entry contains, and the 'policy or SOP' scope merely restates the documentType enum.

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. It is not verbose, but its brevity comes at the cost of coverage rather than from tight editing of necessary content.

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?

The output schema covers return values, so that gap is acceptable, but for a four-parameter paginated list tool with 0% schema description coverage the definition leaves required identifier semantics, pagination, and version ordering unaddressed.

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 compensate, yet it says nothing about documentId, documentType, limit, or offset. An agent must infer pagination semantics (default 25, max 100) and the required identifier pair entirely from the JSON Schema.

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: reading the version history of a document, scoped to policies and SOPs. It is distinguishable from get_policy/get_sop by naming 'version history', though it does not name any sibling explicitly.

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 indication of when to use this versus get_policy, list_policies, or export_policy_pdf, and no prerequisites such as which document types are valid or how to obtain a documentId. Usage is only implied by the phrase 'version history'.

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