publish_survey

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

Annotations already indicate no read-only, idempotent, or destructive hint. The description adds that publishing makes the survey live at its public URL and returns a status response. No hidden behaviors or contradictions.

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 efficiently structured with a clear first paragraph and bullet-like argument descriptions. Every sentence adds value without redundancy.

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?

The description covers input parameters, return values, valid states, and related tools. It lacks detail on error handling but mentions an error object. Given the simple action, it is nearly complete. Minor gap: no mention of prerequisites like authentication.

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?

The description adds meaning for 'list_id' and 'survey_id' beyond schema titles by stating their sources (from list_audiences, list_surveys). However, the optional 'account' parameter is not mentioned. With 0% schema coverage, this is a partial compensation.

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 clearly states the action ('Publish a survey, making it live at its public URL') and the resource. It distinguishes from siblings like 'unpublish_survey' and 'list_surveys'.

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?

Explicitly states valid states for the survey (draft, unpublished, edited), suggests using 'list_surveys' to find IDs, and mentions 'unpublish_survey' as an alternative. This provides clear when-to-use guidance.

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