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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false), so the bar is lower, and the description still adds non-obvious behavior: visibility=internal hides the note from clients while the default all is client-visible, plus a pointer to the field/status documentation. It omits duplicate-handling and what the call returns, but the visibility/privacy semantics are genuine added value.

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?

Four short sentences, front-loaded with what is saved and from where, then visibility semantics, then the exclusion, then the doc link. Nothing is padded, though the trailing documentation URL is a mild deferral of content that could have been inlined.

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 6-parameter mutation with a nested anchor object, low schema coverage, and no output schema, the description covers visibility and anchor optionality but says nothing about what the tool returns (e.g., the created feedback id) or about body/version_id behavior. Adequate to call it correctly in the common case, incomplete for the full 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?

Schema description coverage is only 17%, so the description must compensate, and it does partially: it explains the visibility enum semantics and flags that page/text anchors are optional. It leaves body length limits, the source enum values (only implied by the channel list), version_id semantics, and sectionId unexplained, so roughly half the parameters remain undocumented anywhere.

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?

The description names a specific verb and resource ('Save feedback ... to the relevant page and version') and enumerates the intake channels (meeting, WeChat, call, email), so an agent knows exactly what gets created and where it lands. It does not explicitly contrast itself with the feedback siblings (reply_feedback, list_feedback, set_feedback_status), so differentiation is only implicit.

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?

It states the trigger condition ('feedback the user explicitly supplies') and an explicit exclusion ('Do not collect unrelated conversation history'), which is a real when-not rule. However, it never names the alternative tools an agent should reach for instead (e.g., reply_feedback for responses, list_feedback for retrieval), so routing is left partly to inference.

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