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

With no annotations provided, the description carries the full transparency burden, and it does well: it discloses that there is exactly one draft per account, that it is shared with another assistant, that `missing` comes from the same validation the submission runs, and that fields use the same vocabulary as create_draft/update_draft. It does not cover edge cases like what happens when no draft exists or whether the call has side effects, but the read-oriented verb “Returns” provides reasonable confidence that this is a non-mutating operation.

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?

The description is a compact, two-sentence paragraph with no filler: the primary result is front-loaded, the validation semantic is explained next, and the vocabulary detail is deferred to the final clause. Every sentence adds operational value, and code identifiers are used precisely.

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 zero-parameter read tool with an output schema present, the description is complete: it states what is returned, how to interpret `missing` and `readyToSubmit`, and what to do next after readiness. The missing edge-case notes (e.g., draft absent) are minor against the low complexity and the presence of an output schema.

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 tool has zero parameters, so the input schema is trivially complete and there is little for the description to add about invocation arguments. The description instead adds semantic context about the shape of the returned data, such as prices as a number, licence limited to `standard` or `exclusive`, and videos as YouTube links. This is useful and goes beyond the empty schema, earning the baseline 4 for a no-parameter tool.

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 opens with a specific verb and resource: “Returns the saved publish draft” and immediately distinguishes this tool from siblings by clarifying it reports pre-submission readiness rather than creating, updating, or submitting. It explicitly names related tools (create_draft, update_draft, submit_for_review) and frames its role as the read-side counterpart to those actions.

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?

The description gives clear context for when to use the tool: to inspect the current draft and the validation gaps it still needs before submission. It even routes the user to the next step by stating that when readyToSubmit is true, all that remains is uploading the ZIP and calling submit_for_review. It does not explicitly state “use update_draft when missing has items,” but the vocabulary reference implies how the output connects to update workflows.

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