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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=false, so the safety profile is largely carried structurally. The description adds the useful fact that replies arrive via `list_my_feedback` and that the tool echoes the filed message, but it never states that a filed message cannot be edited or retracted, which matters given destructiveHint=true.

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, front-loaded with the action and followed by the outcome channel. Nothing is padded, and the 'Returns:' prefix makes the result statement easy to scan.

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?

Three flat parameters, full schema coverage and no output schema mean little is left unexplained; the description closes the loop by saying where the answer appears. The only real gap is the absence of any note on irreversibility or on what a 'path' is for, though the schema's own example largely covers the latter.

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%, so `body`, `kind` (with its enum) and `path` are already documented at the field level, including the example path format. The description's phrase 'a bug, an idea or anything else' loosely mirrors the enum but adds no new constraint or format guidance, so baseline 3 applies.

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?

Uses a clear verb ('tell') with a named resource and enumerated content types ('a bug, an idea or anything else') that map onto the `kind` enum. It also names the sibling that surfaces the reply (`list_my_feedback`), so an agent can separate this submit action from the read-side tool without inspecting schemas.

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 intent to file feedback with the Tavern maintainers is implied by 'Tell the people who make Tavern', and the pointer to `list_my_feedback` hints at the follow-up flow. There is no explicit when-to-use vs when-not, and no statement that this is only for product feedback rather than, say, messaging another user (where `send_message` would apply).

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