record_mistake

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

With no annotations, the description must fully disclose behavior. It says the tool records a mistake to strengthen the immune system, but does not explain side effects, such as whether it updates a persistent store, overwrites duplicates, or triggers any other actions. The simplicity of recording may warrant a higher score, but the lack of any behavioral context beyond 'record' is a gap.

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?

The description is concise with two sentences plus a parameter list. The trigger is front-loaded, and every line adds value. No unnecessary words or repetition.

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?

Given the tool has 5 parameters and an output schema, the description covers parameter semantics well but does not mention what the tool returns (e.g., a confirmation or record ID). Since an output schema exists, the return structure might be documented there, but the description could still improve by noting the output format or behavior.

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 provides explanatory labels for each parameter (e.g., 'What went wrong' for mistake, 'WHY it went wrong' for root_cause), which adds meaning beyond the schema's just type/name. It also clarifies severity as 'low/medium/high/critical' and tags as 'comma-separated', filling gaps from the schema's lack of enums or descriptions.

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 explicitly states the tool's purpose: 'Record a mistake so it NEVER happens again.' It uses a strong verb 'record' with the resource 'mistake', and the trigger condition 'Call this EVERY TIME you resolve a bug or make a mistake' clearly distinguishes it from sibling tools like record_decision or record_hypothesis.

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 description provides clear guidance on when to use: 'EVERY TIME you resolve a bug or make a mistake.' It implies a frequent and mandatory usage. However, it does not explicitly state when not to use or mention alternatives, though sibling tools cover different types of records.

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