Commit a freee clock action

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

While annotations already indicate readOnly=false, the description adds critical behavioral context: this is the real mutation, must follow a preparation step, and must not be retried. These safety guardrails go beyond the structured annotations.

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 concise sentences: the first conveys the action and prerequisite, the second states prohibitions. No wasted words, information is front-loaded.

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?

The description, combined with schema and annotations, fully covers the essential context: purpose, prerequisites, and caution against retries. It omits output/error details, but no output schema is present and such details are not critical for this tool's usage.

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 tool description itself doesn't add parameter details, but the schema descriptions already provide strong semantics for confirm (requires explicit approval), fingerprint (SHA-256 from prepare tool), and company_id (unsupported). With 75% coverage, the parameter meanings are clear.

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 specifies the verb 'commit' and resource 'freee clock action', distinguishing it from the sibling prepare_action tool. It explicitly states this creates 'one real punch' as opposed to a preview.

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?

Explicitly states when to use ('only after the matching preview and explicit current-message user approval') and when not to use ('Never call directly or retry automatically'). This gives unambiguous usage direction.

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