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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) by disclosing where the content goes (Tailwind analytics plus an internal staff channel), the privacy constraint (no credentials or personal data, describe rather than quote user content), the language requirement (write in English regardless of conversation language), and that the call fixes nothing and returns nothing usable. These are non-obvious side effects an agent could not infer from the structured fields.

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?

Front-loaded with purpose and trigger, then consent, then content requirements, then exclusions — a sensible order. It is long, and the language/translation passage runs several sentences for one instruction, but essentially every sentence carries an operational rule rather than filler.

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 two-parameter reporting tool with an output schema, everything an agent needs is present: trigger conditions, consent flow, what to put in each field, privacy limits, language policy, post-call user messaging ('tell the user the report was sent and carry on'), and routing to the sibling tool. Nothing material 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real signal: it tells the agent to name the suspected tool in `tool` even when unsure ('a near miss is still useful'), and it models the `description` parameter with a concrete good/bad pair ('list_boards returned 4 boards but the same account shows 11 in get_account' versus 'boards are broken'). That is meaningful guidance beyond the schema's own field docs.

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 — 'Sends a report about a wrong result from a Tailwind tool to the people who maintain these tools' — and immediately distinguishes itself from request_capability for missing-tool feedback. An agent can tell what this does and what it does not do without opening the schema.

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 explicit triggers ('when the user asks to report a problem', a wrong output, a contradicting result, a workaround), an explicit exclusion ('Do not use it for calls that plainly failed: a rejected argument, an expired connection, or an out-of-credits message'), and a named alternative (request_capability). It even specifies the consent protocol — offer to report, send only if the user agrees — which is the exact decision point an agent faces.

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