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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds real value beyond that: the authorization constraint that only the business owner's connection can perform the rejection, and the practical consequence that the item will not proceed.

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?

Two short sentences, each earning its place: the first defines action and effect, the second defines the precondition and the authorization limit. The key constraint is front-loaded.

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 one-parameter destructive action, the agent gets the action, its consequence, the precondition, and the auth requirement, with id provenance delegated to the schema. What it does not cover is the post-rejection state (whether the item can be recovered or re-approved), a minor residual gap.

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 coverage is 100% and the schema itself documents that the id comes from list_pending_approvals or get_briefing. The description only restates "by id" and the singular scope, adding no format or lookup detail beyond the structured field, so baseline 3 applies.

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 (reject/dismiss), the exact resource (one item prepared by the AI team), the identifier used (by id), and the effect (so it doesn't go ahead). This contrasts cleanly with the sibling approve_item without needing to name it.

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?

"Only call when the owner has said to reject it" gives an explicit invocation precondition, which is unusually strong guidance for a mutation tool. It stops short of naming approve_item as the alternative path, so routing is implied rather than spelled out.

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