command_policy_audit

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

Annotations declare a non-read-only, non-destructive, non-idempotent tool, and the description usefully sharpens that: the only write is a redacted JSONL record to the harness audit log, and no command is executed. That is real added context about side-effect scope. It omits any mention of authorization requirements (authority_file, shell_reason) that appear only in the schema.

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?

Two short sentences, front-loaded with the action and immediately followed by the safety-critical constraint. Nothing is redundant or padded.

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 an 11-parameter policy tool with no output schema, the description never says what the evaluation returns (allow/deny verdict, reason codes, the audit record id). The write-scope clarification is helpful, but the missing return-shape information leaves a real gap.

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 100%, so all 11 parameters are already documented in structured data, which sets the baseline at 3. The description adds no parameter-level detail beyond confirming argv is evaluated rather than executed.

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?

States a specific verb pair and resource: 'Evaluate command policy and append a redacted JSONL audit record', plus the key scope qualifier 'without executing the command'. It does not name or distinguish itself against close siblings like command_policy_check or command_fake_run, so an agent must infer the difference.

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?

There is no explicit when-to-use guidance and no named alternative. The phrase 'without executing the command' and 'writes only to the harness audit log' implies the use case (policy evaluation with an audit trail), but nothing tells the agent when to pick command_policy_check or command_fake_run instead.

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