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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description goes well beyond them: it explains exactly what is destroyed (options with collected answers and logic references), that removal retroactively re-interprets data and cannot be undone because re-adding creates a new identity, and that the call fails with a warning unless confirm:true. It also discloses the permission requirement and what the reply reports.

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?

Purpose and the destructive-removal warning are front-loaded, and virtually every sentence carries load-bearing information. It is a single dense paragraph rather than a scannable structure, and the reply-format sentence is partly redundant with the output schema, which keeps it from a 5.

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 destructive in-place mutation on a nested option list, the description covers the failure mode, the confirmation gate, the unsupported operation with its alternatives, and the permission needed. With an output schema present, the brief note on what the reply reports is adequate rather than necessary.

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 material cross-parameter semantics: options are matched by export code, matched codes are relabeled in place with identity preserved, new codes are appended, and omitted codes are silently removed — a partial list is destructive. That operational detail meaningfully exceeds the per-field schema text.

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?

Opens with a specific verb+resource ('Edits an EXISTING question in place') and enumerates the mutable fields (title, requireType, customID, options). It explicitly distinguishes itself from delete_question and add_question for type changes, so an agent can route correctly 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?

Gives explicit when-not guidance ('Changing the question TYPE is not supported — delete_question and add_question instead'), names the preconditions (edit-survey right, explicit user consent before removals), and states the critical calling convention (always pass the FULL option list). Nothing about selection or invocation is left to inference.

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