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

Annotations already declare readOnlyHint=true, so safety is covered structurally. The description contributes that results include verdicts and that some submissions are 'held... waiting for a human', which tells the agent what state means. It omits pagination/limit behavior and ordering semantics for a 'recent' list.

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, result content front-loaded, usage rule second — no filler. It is tight, though the extreme brevity leaves room that could have been spent on the undocumented filters.

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 5-parameter, no-output-schema list tool, the description leaves most of the request surface unexplained: no hint about route values, limit/default page size, form_id scoping, or result shape. An agent can call it, but only with guesswork about the filters.

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 40% across 5 parameters. The description only explains review=true; limit, route (an enum with deliver/hold/drop), and form_id are left undiscussed, so it fails to compensate for the coverage gap. Low-coverage schemas require the description to carry more of this load.

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 (list submissions) plus content of the result (their verdicts), and implicitly distinguishes a filtering mode via review=true. It doesn't name any sibling, but list_forms / label_submission are clearly different operations, so the agent can tell what this does without opening the schema.

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?

Gives one concrete usage rule — 'Use review=true for held ones waiting for a human' — which maps a filter to an intent. However it says nothing about when to prefer this over label_submission or test_submission, nor when not to use it, so guidance is partial and implied.

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