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

Annotations cover only the safety profile (readOnly false, destructive false, idempotent false); the description adds substantial behavioral context they cannot carry — the included revision cycle, the 402 refusal beyond the brief quote, in-job re-presentation with no new charge, lock_violation surfacing, and abandon as the only terminal refusal. This is well beyond annotation coverage.

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?

Purpose and the packet-first prerequisite are front-loaded, and nearly every clause carries operational information. It is dense and heavily parenthetical, which costs some readability, but there is little filler to cut.

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 a multi-branch mutation gate with an output schema present, the description covers the full decision lifecycle, the refusal mode, and the next tool to call, so an agent needs nothing else to invoke it correctly.

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 the baseline is 3; the description nonetheless adds consequence-level meaning to the decision enum (approve records comments as taste without gating, revise re-presents the same gate in-job, abandon terminates) and to lock semantics that go beyond the schema's own text. The remaining schema-documented fields (edits, comments anchors) are adequately covered.

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 states a specific verb and resource — 'Answer the checkpoint packet wait_job reported as awaiting_input' — and immediately distinguishes itself from siblings get_checkpoint (read the packet) and wait_job (the source that signals awaiting_input). An agent can identify this as the resume-the-gate tool without opening the schema.

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?

It gives explicit when-to-use (a packet reported awaiting_input), a prerequisite workflow (read the packet FIRST with get_checkpoint, relay stills + money triple to the human), and explicit follow-up ('then wait_job again'). The revise/lock/abandon branches are each given the condition that selects them.

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