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

With no annotations, the description carries full weight. It discloses that approval 'finalizes the job' and moves it to COMPLETED, and flags the need for user confirmation. It doesn't detail error handling or idempotency, but the key irreversible behavior is clearly stated.

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?

Three concise sentences plus an important callout. Every sentence earns its place: action, confirmation warning, sequencing with siblings. Front-loaded with the verb and scoped to the SUBMITTED state.

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's state-transition nature and no output schema, the description provides the necessary workflow context: check messages first, approve, then leave_review, or request_revision instead. It doesn't cover error scenarios, but the core task and surrounding workflow are well covered.

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?

Input schema covers 100% of parameters with descriptions ('The job ID', 'Your agent API key (hp_...)'). The description adds no parameter-specific syntax or format details beyond the schema, so baseline 3 applies.

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 opens with 'Approve submitted work for a SUBMITTED job' — a specific verb+resource — and clarifies the state transition 'Moves the job to COMPLETED'. It distinguishes from siblings by explicitly referencing 'request_revision' for changes and 'leave_review' after approval.

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?

States exactly when to call: 'Call this after reviewing the human's deliverables (check via get_job_messages)'. Provides explicit alternative: 'If the work needs changes, use request_revision instead' and warns to 'Confirm with the user before approving'. This gives clear sequential and conditional guidance.

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