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

Adds substantial context beyond annotations: auto-creates the 'External for {survey}' list and unknown custom fields, PersonalizedID is not uniqueness-checked, links fall back to the generated internal ID, email fires only on explicit true, and the write is verified by readback. This goes well past destructiveHint/openWorldHint and materially affects how an agent should call it.

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?

Dense single paragraph with the primary purpose front-loaded; every clause carries information (side effects, defaults, return). It is longer than ideal and the nested parentheticals make it slightly hard to scan, but no sentence is filler.

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 non-idempotent, destructive, open-world mutation with an output schema and a nested object parameter, the description covers the risky behaviours (auto-creation, invitation email, non-unique ID, readback verification). Nothing an agent must know before invoking is missing.

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 the baseline is 3, but the description adds semantics the schema only implies: the uniqueness behaviour of personalizedID, its role in the personal link, and the exact sendInvitation trigger. That is meaningful value over the structured fields.

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?

Specific verb+resource: "Creates a respondent in the survey's respondent list." It distinguishes this tool from siblings like create_survey_response by naming the respondent list entity and by enumerating the side effects (auto-created list, custom fields). An agent can tell what it does without opening the 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?

Explicit conditional guidance for sendInvitation ("sent ONLY when explicitly true — leave it off unless the user clearly asked"), which is exactly the kind of default-trap an agent needs. It does not, however, contrast this tool with alternatives or state prerequisites beyond the optionality of PersonalizedID.

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