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

Annotations only tell the agent this is a destructive, open-world write; the description adds the genuinely non-obvious behavior: the elicitation dialog is off by default, a decline marks the draft rejected and returns success false with consent 'declined', and a 40-second no-answer is treated as chat confirmation. It also lists preconditions (must be pending, owned by this user, not expired) and explains that an elapsed scheduled time cannot be approved as-is, which is exactly the destructive-edge-case context annotations cannot convey.

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 most consequential constraint — publish now, only after explicit user confirmation — is front-loaded in the first two sentences, with the consent-dialog mechanics and precondition list following in descending order of importance. It is dense and one paragraph long, but every clause carries operational information (consent source, decline handling, timeout, expiry, return shape) and nothing is 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?

There is no output schema, and the description compensates by stating what comes back: per-platform success/failure for immediate publishes and scheduled post IDs for scheduled publishes. Combined with the precondition list and the elapsed-time recovery path via scheduledFor, an agent has enough to call the tool and interpret the result correctly.

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 both parameters are already documented, and the schema's own scheduledFor text already covers 'time has passed or the user wants a different time' plus 'confirm the new time first.' The description's closing note on elapsed scheduled drafts restates that rather than adding new meaning, so it sits at the baseline-3 level for a fully documented schema.

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 — 'Publish a pending draft NOW' — and immediately discloses the divergent behavior for scheduled drafts (moved into the scheduled queue). It also constrains the resource to drafts created via create_post_draft, schedule_post_draft, or create_x_article_draft, which separates it from publish_now and publish_scheduled without the agent needing to open those schemas.

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?

It gives an explicit precondition ('Call this AFTER the user has explicitly confirmed in chat') plus a hard prohibition ('Do NOT call without explicit user consent'). It also covers the tricky branch — the settings-based confirmation dialog, what a decline means, and that a timeout counts as consent — and states 'never retry; ask the user' on decline. That is when-to-use, when-not-to-use, and alternative-path guidance all in one.

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