record_run

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

The description reveals several behavioral traits beyond the input schema, including validation against schema_version:2, size enforcement via MAX_RECORD_BYTES and RECORD_TOO_LARGE, file mode 0o600 on first create, and control character stripping. With no annotations provided, the description carries the full burden and covers important mutation and safety details, though it could mention error handling beyond overflow.

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 a single focused paragraph that front-loads the core action. Each sentence provides distinct value: purpose, contract, validation, size limit, caller responsibility, file mode, and string sanitization. It is concise and structured logically, though it could benefit from bullet points for readability.

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 complexity of the tool (nested record object, multiple validations, file operations), the description covers key aspects: action, constraints, single-writer model, and data integrity responsibilities. However, it lacks any mention of return values or success indicators, and no output schema is provided. This gap prevents a perfect score.

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 input schema is extremely rich with many nested properties, so the schema itself explains parameters thoroughly. The description adds context about validation and constraints but does not explain individual parameters like workspace_root or record properties. With 0% schema description coverage, the description should ideally compensate more, but the schema's high detail keeps the baseline at 3.

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 action ('Append one RunRecord'), resource ('RunRecord'), and target file ('.squad/runs.jsonl'), distinguishing it from sibling tools like 'list_runs' (listing) and 'record_learning' (other recording). It leaves no ambiguity about what the tool does.

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 explicitly defines a 'single-writer contract' and lists the allowed calling skills with phase contexts (e.g., squad Phase 1 + Phase 10). It also alerts the caller to match in_flight↔terminal rows by id. However, it does not explicitly state when not to use this tool compared to other recording tools, missing a full exclusion clause.

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