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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=false) by disclosing the retry lifecycle: the piece re-enters review, only one revision is permitted, and a second round of editor changes results in rejection. It also notes the API key requirement. Minor gap: it does not say what a successful call returns or whether the submission goes back to a pending state.

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?

Four short sentences, zero waste, each adding a distinct fact (precondition, content format, review consequence, revision limit, auth). The precondition is front-loaded ahead of the caveats.

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?

Given a large nested article schema and no output schema, the description covers the operational essentials an agent needs: eligibility, full-article-not-diff, one-shot revision risk, and auth. Not fully complete because it leaves the post-call state (status after resubmission, error conditions such as a non-eligible submission) 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 reported at 0%, so the description has to carry parameter meaning, and it does make one important addition: the article must be the complete corrected article, not a diff. Beyond that it says nothing about submission_id (uuid) or the nested article fields, which the schema documents unevenly.

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 (resubmit a submission) plus the exact precondition that selects it: status must be needs_revision. This cleanly separates it from submit_article and submit_correction without the agent needing to open any 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 clear when-to-use context (only for submissions in needs_revision) and routes the agent to get_submission to obtain the editor_notes to address. It does not explicitly state what to do if the status is something else, but the precondition makes that largely self-evident.

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