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

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description adds substantial context beyond that: the contents of the packet (stage artifact, presigned stills, critic verdicts, money triple, reviewUrl) and the instruction to relay evidence rather than raw JSON. It stops short of describing pagination, expiry, or error behavior for an unresolvable checkpointId.

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?

Front-loaded with the core definition and organised around what the packet contains and how to act on it. It is dense but a single long paragraph; the trailing webhook/wait_job clause restates how the decision is learned and could be trimmed.

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?

An output schema exists so return values need not be explained, yet the description's account of packet contents is what drives the agent's downstream behaviour (relaying the money triple and reviewUrl). Combined with the resume hand-off, the definition is complete enough to invoke and act on 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 coverage is 100% and there is only one parameter whose schema description ('checkpointId (path).') is thin. The description compensates by explaining where checkpointId originates — the wait_job awaiting_input payload — which is meaning the schema itself does not carry.

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+resource ('Read a checkpoint packet') and defines what a checkpoint is — 'the durable approval unit a held compose pauses at' — which separates it cleanly from list_checkpoints and wait_job in the sibling set.

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 names the trigger condition ('when wait_job reports awaiting_input with {checkpointId, stage, version}') and the follow-up action ('Answer an awaiting packet with resume(checkpointId, ...)'). It also distinguishes hosted vs non-hosted review flows, leaving no ambiguity about when to call this versus its alternatives.

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