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

The description says the review happens 'without recording it', which implies a read-only preview, while annotations declare readOnlyHint=false. That is a direct conflict about whether the tool mutates state, and the description provides no additional behavioral context about idempotency or side effects.

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?

It is a single short sentence with no filler, and the no-recording constraint is front-loaded. It is arguably too terse for the tool's complexity, but there is no structural waste.

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 tool with five parameters, four required, an idempotency key, and no output schema, the description is far too sparse. It leaves the agent without parameter guidance, alternative routing, or a coherent safety profile given the readOnlyHint conflict.

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?

The schema has five parameters with 0% description coverage, including a required idempotency_key, offer_id, decision enum, and comment. The description mentions only an 'approval decision' and gives no meaning for offer_id, idempotency_key, request_id, comment length constraints, or the approve/reject enum.

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 verb 'Review' and resource 'approval decision' are present, and 'without recording it' clarifies the preview nature. However, it does not explicitly say 'preview' or distinguish this tool from siblings such as yardstick_offers_approval_review and yardstick_offers_approval_bind.

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 phrase 'without recording it' implies this is a dry-run before the real approval action, but the description never states when to use this versus yardstick_offers_approval_bind or yardstick_offers_approval_review. No explicit alternatives or prerequisites are given.

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