record_learning

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

The description discloses side-effects ('writes to disk') and explains the impact on future runs. Since no annotations are provided, the description carries full burden. It lacks details on permissions or error behavior but provides good context for a write operation.

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, front-loading the main action and including essential context about side-effects and future behavior. No unnecessary words.

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 12 parameters and no output schema or annotations, the description is insufficient. It does not explain the parameters or return value, leaving the agent without critical information for correct invocation.

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 mentions 'team decision (accept | reject)' which maps to the 'decision' parameter, but does not explain any of the other 11 parameters. With 0% schema description coverage, the description fails to compensate for the missing parameter semantics.

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 clearly states the verb 'append' and the resource '.squad/learnings.jsonl', and specifies the action of recording a team decision (accept/reject). It distinguishes from sibling tools like prune_learnings and read_learnings by focusing on appending a decision.

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 explains the purpose: to prevent re-suggestion by injecting decisions into future prompts. It notes that the caller is responsible for user confirmation, implying appropriate usage. However, it does not explicitly differentiate from alternative sibling tools.

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