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

Annotations only declare readOnly=false, destructive=false, openWorld=false; the description adds far more — the draft-only mutation constraint, the immutability rationale, and the full confirmation protocol (status='confirmation_required', action_id, plan_token, confirm_action). It stops short of describing failure modes or what the plan contains, but the behavioral picture is well beyond what 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?

Front-loaded with the core action and lifecycle position, then constraint-by-constraint, with the confirmation protocol last where an agent will look for it. It is dense and quote-heavy, but nearly every clause carries decision-relevant information; only the parenthetical about empty versions is arguably extra.

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?

No output schema exists, and the description compensates by describing the exact confirmation response shape and the handoff to confirm_action. Combined with the draft-only rule and cross-references to hr_feedback_report, it is nearly complete; the main remaining gap is which label fields are required versus optional and how missing 'options' failures surface.

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 0% schema description coverage across 10 parameters, the description does necessary work: 'key' as the stable analytics handle with per-version uniqueness, 'type' as a closed set with the conditional 'options' requirement for choice fields, 'info_block' taking no answer, 'analytics_role' as the trigger for hr_feedback_report counting, and 'order' defaulting to the end. It leaves label_uk/label_en, help_text, required, and version_id semantics (beyond naming) undocumented.

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+resource: 'Add one QUESTION to a form's draft version'. It also positions the tool in the lifecycle between hr_create_form and hr_publish_form_version, which lets an agent distinguish it from both siblings 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 explicit when-to-use (the step between create and publish, without which nothing can be published) and when-not-to-use ('Only a DRAFT accepts fields — a published version is frozen'). It also names the alternative execution path, confirm_action, for actually committing the write.

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