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

Goes well beyond the destructive/openWorld annotations by disclosing that publish is one-way (the participant link goes live), that questions replacement is whole and refused with `invalid` once responses exist, and that the call may return `needs_confirmation`. Null-clearing semantics for completionRedirectUrl and autoAnalyzeTarget are also spelled out, which the annotations cannot convey.

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?

Front-loads the highest-stakes behavior (publish one-way, then closed) and every clause carries information. It is a single dense run-on rather than cleanly separated sentences, which slightly hurts scannability, but there is no 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 12-param destructive mutation with no output schema, the description covers the consequential behaviors, error signaling (needs_confirmation, invalid), and id sourcing. It leaves approvalId unexplained and does not sketch the return payload, so it is strong but not exhaustive.

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?

With only 33% schema description coverage across 12 params, the description compensates heavily, explaining the meaning of title, questions (whole replacement), adaptiveFollowUps, endChatEnabled/endChatFocus, completionRedirectUrl, autoAnalyzeTarget, publish, closed, and where studyId comes from. It adds real semantics (null clears, one-way, lock behavior) rather than restating types.

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 specific verbs (publish, close, edit) and the exact resources touched (title, questions instrument, adaptiveFollowUps, closing chat, completionRedirectUrl, autoAnalyzeTarget). It also names siblings prism_studies_get (for reading the shape first) and prism_studies_list_workspace (for ids), so an agent can tell it apart from the read and list tools without opening a 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?

Gives concrete conditional guidance: read prism_studies_get before replacing questions, and when the instrument is LOCKED the answer is a new study rather than this tool. That points to an alternative, but it never states the broad when-to-use vs prism_studies_delete or prism_studies_series_update, so it stops short of full coverage.

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