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

Annotations already mark destructiveHint=true, but the description adds critical context: the action is public and customer-visible, and if the publish fails, the text is preserved with a manual fallback status. This reassures the agent that no data is lost, going well beyond the structured annotations.

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 two sentences, front-loaded with the action verb and key constraint. Every sentence adds value: the first states the purpose and approval requirement, the second covers failure behavior. No word 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?

For a destructive, open-world action with no output schema, the description provides sufficient context: it explains the public nature, the approval condition, and the failure fallback. It tells the agent what happens on both success and failure, making the tool's behavior predictable.

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 both parameters ('text' and 'review_id') already described clearly. The tool description does not add new parameter-level details; it reinforces the 'exact text' requirement already present in the schema. Baseline 3 is appropriate since the schema carries the parameter 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?

The description starts with the specific verb 'PUBLISH' and clearly identifies the resource: 'a reply to this review's public Google profile.' It distinguishes from sibling draft_reply by explicitly marking this as the publish action, and adds the important qualifier that it is customer-visible.

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 an explicit when-to-use condition: 'call it ONLY when the user has explicitly approved this exact text.' It also explains the fallback behavior if Google rejects the publish, helping the agent understand the outcome and alternative path. This effectively tells the agent not to call it without approval.

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