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

Annotations already declare non-read-only, non-idempotent, open-world behavior, and the description adds real value on top: the 422 test_inputs_not_passing refusal with per-input reasons, the 409 connect_not_ready case, and the required API scope. It does not disclose whether a failed publish consumes anything or what the response contains.

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?

Three tight sentences, front-loaded with the outcome, then refusal conditions, then auth requirement. Nothing is redundant and every clause carries operational information.

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 single-parameter mutation with no output schema, the description covers the state transition, failure modes, and auth needs. It stops short of saying what the caller gets back (e.g., a new version identifier), which is the one remaining gap without 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?

Schema coverage is 100% with a single parameter whose description already ties it to alterlab_listing_draft_create. The description adds no new syntax or meaning for draft_id, only the indirect reference to 'this exact manifest', so the baseline 3 applies.

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?

Specific verb ('Publishes') plus resource ('the draft') plus the resulting state ('new immutable version in pending_review'). An agent knows exactly what happens to the draft and where it lands, which distinguishes it from the sibling draft-create and draft-test tools.

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?

Preconditions are stated concretely: the last test must have run on this exact manifest and every test_inputs entry must pass, paid listings need verified Stripe Connect, and the API key needs listings:write. It implies the sibling alterlab_listing_draft_test as the prerequisite step. It does not explicitly route to alternatives when the preconditions fail, so it falls just short of a 5.

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