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

Annotations only provide coarse hints (not read-only, destructive, open-world, idempotent); the description adds the credit cost, the refund condition, the fast-path latency ('live link within seconds'), and the fallback path where a human review can hold the release up to 24 hours with a stated reason. That is substantial behavioral context an agent cannot infer from the structured fields.

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?

Front-loaded with the purpose, then the gating condition, then cost/refund, then outcomes — no sentence is padding. It is slightly denser than necessary with credit and timing details packed into one run-on sentence, but nothing is wasted.

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, so the description must cover return values, and it does: a live link within seconds, or a pending-review message with reason and expected duration. Combined with the cost and refund rules, an agent has everything needed to call it and set expectations.

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 100% and only two parameters exist, so the schema already documents both fields; the description reinforces the meaning of confirm ('the user saw the preview and said to publish') but adds nothing about release_id. Baseline 3 is appropriate when the schema carries the semantics.

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 ('Publishes a draft press release') plus the external side effect ('tells search engines about it'). This clearly separates it from create_release, update_release, and preview_press_release, and the draft-vs-live distinction is explicit.

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 a hard precondition — 'Only call this after the user has seen the preview and clearly said to publish, and set confirm to true' — which functions as both when-to-use and when-not-to-use. It implicitly routes the agent through the preview step before publishing rather than any sibling mutation tool.

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