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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write, so the mutation profile is visible. The description adds useful guardrails (only on explicit user feedback, don't persist question/source text), but says nothing about what is persisted, duplicate handling for the non-idempotent write, or what happens to prior feedback.

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?

Two tight sentences, front-loaded with the core action, followed by the invocation condition and the data-handling constraint. Nothing is wasted.

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 six-parameter mutation tool with zero schema descriptions and no output schema, the description leaves the key required field taskFamily undefined and does not indicate the return value or persistence behavior. It covers triggering but not the information an agent needs to populate the call correctly.

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 description coverage is 0% across six parameters, so the description must carry the semantics and largely does not. The outcome enum values are inferable from the accept/reject/correct/failure wording, but the required taskFamily parameter — the most ambiguous field — is never explained, nor are projectId, capabilityId, or toolName.

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: recording explicit user feedback about a ResearchPilot capability/tool outcome. It is clearly distinct from siblings like update_user_preferences or save_work_artifact, though it never names an alternative explicitly.

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 a firm trigger condition — call only when the user explicitly accepts, rejects, corrects, or reports success/failure — which is a genuine when-to-use rule. It adds a negative constraint about not storing the research question or source text, but offers no alternative tool routing or exclusion against other persistence tools.

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