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

Annotations already mark readOnlyHint=true, but the description adds meaningful behavioral context: responses are unread, ordered oldest-first, and reading does not acknowledge them. The note that acknowledge_feedback_responses must be called separately prevents a common misuse, going well beyond structured annotation data.

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?

Three tightly scoped sentences deliver the core purpose, usage trigger, ordering, non-acknowledgment behavior, and follow-up instruction with no filler. Key operational facts are front-loaded.

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?

With a full output schema, 100% parameter schema coverage, and annotations carrying safety semantics, everything an agent needs is present: when to call, what it returns semantically, ordering, and post-processing action. Nothing important is left to inference.

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?

Input schema description coverage is 100%, so the schema already documents limit and cursor. The description adds context on response ordering and the acknowledgment follow-up, but no additional parameter-level semantics beyond what the schema provides; baseline 3 is appropriate.

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 uses a specific verb ('Fetch') and resource ('unread Charming staff responses to feedback'), clearly distinguishing this read tool from the sibling acknowledge_feedback_responses. It also conveys the unique unread/acknowledgment semantics that separate it from other feedback tooling.

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?

The description explicitly tells the agent when to use the tool ('when a feedback-responses-available advisory appears') and instructs the follow-up action of calling acknowledge_feedback_responses after processing. This gives clear, decisive routing guidance relative to its sibling tools.

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