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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true); the description goes well beyond that by disclosing where the transcript lands ('stays on the study', 'never lands in Compass'), that it joins the next analysis run, that the guest needs no account, and that it may return `needs_confirmation`. It stops short of auth/permission requirements, rate limits, or idempotency, so it is strong but not exhaustive.

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?

Three tight sentences that front-load the action and the returned invite link, then layer the side effects and the optional parameter's behavior. No filler and no repetition of the title.

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 5-parameter, no-output-schema mutation with 20% schema coverage, the description covers the return value (invite link) and the confirmation edge case, but the undocumented approvalId and intervieweeName leave an agent unable to judge what those inputs do or whether they are needed.

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 only 20% (just `workspace`), so the description must carry the load. It explains focusPrompt well ('briefs the interviewer on what to dig into; omitted, it explores the study's territory') but leaves approvalId, intervieweeName, and studyId entirely undefined, so most parameters remain opaque.

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 ('Creates a one-on-one AI-led interview on a study') plus the concrete return artifact (invite link). This clearly separates it from the sibling prism_interviews_list, which lists rather than mints interviews.

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 implies the usage context (forward the invite to a guest who needs no account) and explains what focusPrompt does when supplied or omitted, but it never states when to choose this tool over near-neighbors like prism_series_create or prism_series_launch_wave, nor any exclusions or prerequisites.

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