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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, non-idempotent), and the description adds substantial context beyond that: it is free/never charged, rate-limited to 20 per day per workspace with the specific error feedback_rate_limited, recommends consolidating into one message, warns against including secrets or customer personal data, and notes a runId outside the workspace is ignored. It even states the return shape.

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?

Purpose and invocation triggers are front-loaded, and nearly every clause carries operative information rather than filler. It is a dense semicolon-chained block, which slightly reduces scannability for the optional-parameter details, but nothing is genuinely wasteful.

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 5-parameter mutation tool with no output schema, the description supplies the missing return value ({ feedbackId, status: 'new' }), the rate-limit failure mode, data-hygiene constraints, and per-parameter guidance. An agent has everything needed to invoke it correctly on the first try.

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 0%, so the description must carry the full burden, and it does: it explains kind semantics, what message should contain (what you did, what you expected, what happened) plus the 4000-character limit, that runId/endpointId are optional but materially aid actionability, and that rating is optional on a 1-5 scale. This adds real meaning beyond the bare JSON schema constraints.

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 ('tell the looot team what went wrong or what would help') and anchors it to equivalent surfaces (POST /v1/feedback and the `looot feedback` CLI). It is clearly distinguishable from siblings like runs_get or capability_request, which handle inspection and access rather than reporting.

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?

Explicit triggering conditions are enumerated: wrong/empty/oversized answers, unclear docs or errors, missing provider or job (kind 'idea'), and things that worked well (kind 'praise'). The kind enum is disambiguated in prose, so an agent knows when to choose bug vs idea vs praise vs question without inference.

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