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

The description carries real information beyond the annotations: admin-only authorization with an explicit refusal for non-admins, and the ordering semantics that decisions are applied *before* the listing is produced. That ordering detail matters given destructiveHint=true. It does not address reversibility of 'retire', idempotency, or what happens with unknown ids, which keeps it below 5.

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?

Three sentences, front-loaded with the access restriction that determines whether the agent should call it at all. The middle sentence is dense — three output sections packed into one — but every clause carries distinct information. 'Free.' is terse and purposeful rather than filler.

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?

With no output schema, this description does the work of explaining the return shape across all three sections, and it flags the auth gate and the mutation-before-read ordering for a 4-parameter destructive tool. What remains thin is the per-parameter contract, partly covered by the schema's single 'retire' description.

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 only 25%, and the description names all four parameters (approve, reject, retire, edit) and ties them to domain objects — candidate rules versus live rules. However it never says which pool 'edit' targets, what id format is expected, that edit text is capped at 160 characters, or that each array is limited to 50 items. It compensates partially, consistent with a 3.

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 names the resource (the 'brain' rule set) and spells out three concrete outputs: candidate rules awaiting approval with their lessons, live rules with failure/dispute stats, and a results pool comparing this week to four weeks prior. It also states the tool can apply approve/reject/retire/edit decisions. It stops short of 5 because no sibling tool is named for contrast, though the brain domain is distinct enough in the sibling list that confusion is unlikely.

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?

It gives a clear gating condition ('For Shipfound's own admins only; anyone else gets a refusal') and tells the agent that passing approve/reject/retire/edit both applies decisions and returns the review view. No explicit alternatives are named, and there is no sibling brain tool to route against, so 4 rather than 5.

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