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

Beyond the annotations (writable, non-destructive, non-idempotent, closed-world), it discloses real behavioral traits: 30-question/30-choice limits, stable surveyId plus expectedRevision semantics, the rule that published question IDs keep their meaning, and that personalization permission is rechecked at dispatch. This is far more than the annotations carry.

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?

It is front-loaded with the core action and keeps to a tight block, but the second half is heavily compressed with parenthetical schema shorthand and at least one typo ('Up to30 questions and30 choices'), which slightly impedes scanning.

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 tool whose payload schema is effectively blank and that has no output schema, the description covers the write semantics, limits, ID rules, and targeting vocabulary well. It does not say what a successful save returns (e.g., the new revision to feed back as expectedRevision), which matters for the revision workflow.

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 input schema exposes the payload only as an opaque additionalProperties object, so the description must carry the burden — and it does, spelling out the draft shape ({name,title,description,communityId,questions:[...]}), question types, and the surveyAnswer/surveyAnswered targeting operators (eq/contains/gte/lte/known/unknown, eq0/1). That is substantial meaning added beyond the 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 (save) plus resource (survey draft) and immediately disambiguates from publish_email_survey by stating 'Saving does not publish or contact anyone.' An agent can distinguish it from siblings like publish_email_survey and inspect_email_surveys 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?

It establishes the operating context clearly (drafting/saving versus publishing or contacting recipients) and points to the workflow guide resource socialloop://guides/email-campaigns. However, it never names the alternative tools (publish_email_survey, inspect_email_surveys) or the exact condition that selects this one over them, leaving that to inference.

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