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

Beyond the annotations (which only say non-read-only, non-idempotent, non-destructive), it discloses useful operational facts: the report is free, the Kelpo team reads every report, there is no automatic analysis, and the agent must never promise a refund or fix. It does not say what happens to a duplicate submission beyond 'not one per call', and does not describe the confirmation response.

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 the defect taxonomy are front-loaded, and most sentences carry decision-relevant content (batching rule, evidence requirements, no-refund policy). It is dense and run-on, and the trailing raw 'Arguments:' JSON fragment adds little over the schema.

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 nested, non-read-only reporting tool with no output schema, the description supplies timing, content expectations, human-review behavior and the follow-up sibling. Minor gaps remain: no mention of the response shape or duplicate-handling, and the kind taxonomy is left to the schema.

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?

The description covers the practical payload shape ('job ids and shot, what you observed (quote values, messages, heard words) and what you expected'), which maps to the key nested fields and reinforces the quoted-evidence expectation. However, the 13-value 'kind' enum, plus 'language', 'assistant' and 'project_id', are never explained in the description, leaving real gaps at low reported schema coverage.

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 opens with a specific verb and resource ('Tell Kelpo what went wrong') and then enumerates the exact categories of defects it accepts (take defects, price/charge, contradictions, slow renders, refused features, docs). It is clearly distinguishable from the status-reading sibling kelpo_get_report, which it names.

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?

It gives explicit timing guidance ('Send one report when the problems are known (e.g. after delivery)'), an explicit anti-pattern ('not one per call'), and routes status-checking to kelpo_get_report. An agent knows both when to call this and when to call the alternative.

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