publish

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

Annotations only say it is a non-read-only, non-destructive, non-idempotent write. The description goes well beyond that: a future publishAt leaves the draft unpublished and invisible to readers until go-live, surfaces it under Scheduled publishing, and re-invocation reschedules. It also discloses the language-mismatch refusal gate and its override, which is real behavioral context no structured field carries.

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?

Purpose is front-loaded, then the language-branch hazard, then scheduling, rescheduling, and a final warning. Every sentence carries distinct operational information and the capitalized emphasis flags the two highest-risk misinterpretations without padding.

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 6-parameter mutation with no output schema, the description covers the important failure and side-effect modes (mismatch refusal, invisible-until-scheduled, reschedule). It does not describe what a successful call returns or any error shape, but with annotations covering safety and the schema fully documented, the remaining gap is minor.

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%, so the baseline is 3, but the description adds genuine meaning beyond it: 'locale' is characterized as a LANGUAGE BRANCH with concrete failure semantics, and allowLanguageMismatch is explained as a deliberate override. publishAt's scheduling (not immediate-publish) semantics are clarified. expireAt is left entirely to the schema, which documents it adequately.

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 ('Publish the working draft of a content item for a locale'), which cleanly separates it from siblings like unpublish, discard_draft, and update_content. The scope (working draft, per-locale branch) is precise enough that an agent can select it without opening 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: with publishAt it schedules, without it goes live now, and re-calling either reschedules or publishes. It also supplies an explicit when-not ('NEVER fake scheduling by putting the date in a data field'). It never names the natural alternatives (unpublish, discard_draft, update_content), so sibling routing is left to inference.

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