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

Annotations already declare this as a non-readonly, non-destructive write, so the bar is lower. The description adds real context beyond them: a hard 300-character cap and the fact that "Reports are read, not published," which reassures the agent the submission is private. It does not mention whether duplicate submissions are deduplicated or what the call returns.

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 short sentences with zero filler; the purpose leads and the constraints (one issue per call, 300 characters, not published) follow immediately. Every clause earns its place.

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 three-parameter submission tool with full schema coverage and no output schema, the description covers purpose, limits and audience. The only gap is what the agent gets back after sending, which is minor for a fire-and-forget feedback call.

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 100%, including a fully documented enum for kind, so the schema carries the parameter burden. The description's 300-character limit restates what the message property already says, adding little. 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?

States a specific verb (tell the maintainers), a specific resource (feedback about AcuiQ), and enumerates the cases it covers: missing content, wrong content, breakage. All siblings are read-only lookup tools, so there is no plausible confusion about which tool to pick for this action.

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?

"what you needed and did not find, what is wrong, or what broke" maps cleanly onto the kind enum and tells the agent when this tool applies. "One issue per call" gives batching guidance. It stops short of explicit exclusions or naming an alternative channel, so not a 5.

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