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

With no annotations, the description carries the full burden and does disclose the key side effect that labeling 'real' delivers a held or dropped submission. However, it omits reversibility of the action, whether the readOnly-style safety profile applies, and auth requirements (the api_key behavior lives only in the schema).

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 sentence with the consequence front-loaded in the parenthetical; no filler and nothing redundant.

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 small two-required-param mutation tool with no annotations or output schema, the crucial behavioral fact (delivery on 'real') is stated. Remaining gaps are minor: no error/failure behavior and no explicit note on irreversibility.

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 leaves the enum values 'real' and 'spam' undefined, so the description's explanation that 'real' triggers delivery adds real meaning beyond the schema. submission_id and api_key are covered by the schema itself, so 67% coverage is largely compensated.

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 (mark) and resource (submission) plus the two terminal states (real/spam), and the parenthetical clarifies the consequence of labeling something real. It doesn't name a sibling to distinguish itself from, e.g., doorman_test_submission, but the purpose is unambiguous.

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 explicit when-to-use guidance, no prerequisites, and no mention of alternatives such as doorman_test_submission or doorman_list_submissions. The held/dropped parenthetical hints at context but never states the condition under which an agent should call this tool.

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