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

The description adds behavioral details beyond the readOnlyHint annotation: newest-first ordering, time-limited PDF preview, included fields, and the default pending filter. This gives the agent useful expectations about the output and its constraints without contradicting the annotations.

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 compact and front-loaded with the main purpose, followed by the default behavior and the follow-up tool. It is bilingual, which duplicates content, but both languages carry the same key information and the extra length is modest and intentional for accessibility.

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 read-only list tool with five optional parameters and no output schema, the description conveys the key return elements (approvalIds, PDF preview, cost, reason, deadlines) and the default pending state. The main missing piece is a note about pagination behavior, but limit/offset are self-explanatory from the schema.

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?

With 80% schema description coverage, the baseline is 3. The tool description does not add parameter-specific semantics; it only mentions default pending status, which relates to the 'status' parameter already documented in the schema. The 'reasoning' parameter lacks both schema and description coverage, but the high overall schema coverage keeps this at baseline.

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 states a specific verb and resource: 'Lists your account's approvals, newest first' with concrete fields (PDF preview, cost, reason, deadlines). It also distinguishes itself from the sibling approval_decide by explicitly directing the agent to use that tool for the returned approvalIds, which is more than a generic listing description.

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 provides clear context for when to use this tool: to retrieve approvals before making a decision, and explicitly names approval_decide as the next step. It also clarifies the default status filter ('Only the pending approvals by default'). However, it does not explicitly state when not to use it or mention alternatives like approval_status_app for single-status lookup.

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