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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered, and the description adds genuine behavioral value beyond that: it decodes the non-obvious status vocabulary (yellow vs red carry meanings an agent cannot guess) and states that the response includes reason codes and per-check automatic check results. What it does not disclose is whether the status is polled/live or cached, and the shape of the reason codes.

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?

A single front-loaded sentence that identifies the subject first and then spends the remainder on the enumerated states, each with a brief parenthetical only where the term is ambiguous. There is no filler, no restatement of the title, and nothing an agent would want trimmed.

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 and no annotation coverage of return values, the description carries the burden of explaining what comes back, and it does so for the headline field (status) plus the presence of reason codes and automatic check results. It is nearly complete for a single-parameter read tool; only the structure of the reason codes and check results, and whether repeated polling is expected, remain unstated.

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 description coverage is 0%, so the schema supplies only a name, a uuid format, and a regex for submission_id, with no prose meaning. The description does not mention the parameter at all, though the name submission_id is largely self-explanatory and the uuid format constrains it adequately. This is the minimum viable level rather than strong compensation.

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 exact resource (a submission) and the exact information returned (its status), and enumerates the possible states with short glosses such as 'yellow (waiting for review)' and 'red (held for the owner of the directory)'. An agent can immediately tell this is a read of submission state rather than a search or mutation. It stops short of contrasting itself with the similarly named sibling get_claim_status.

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?

There is no when-to-use guidance, no prerequisites, and no mention of when to prefer this over siblings like get_claim_status or get_listing. The context of use is only implied by the tool name and the state vocabulary; an agent must infer that this is the tool to call after submitting or while polling for a review decision.

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