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

Annotations indicate a destructive, non-idempotent write operation. The description adds substantial behavioral context beyond annotations: it is asynchronous (queue + poll), mentions stale-edit protection, and imposes a system-ArtDirection draft-only constraint. These details are not in the annotations and are crucial for correct usage.

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?

The description is three sentences with no filler. It front-loads the core purpose, then explains save modes and constraints, and ends with the polling instruction. Every sentence earns its place.

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 is a queue-based revision with 7 parameters and no output schema, the description covers the essential aspects: async behavior, save modes, system constraint, and how to retrieve results. It omits error handling and prerequisites, but these are secondary for a queue tool and the guidance is sufficient for correct invocation.

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 adds value by clarifying that existing authoring references are included automatically and explaining the save parameter's behavior in plain terms, which is not fully captured in the schema. It also implies that sources are additive.

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 states the tool queues a feedback-driven revision of an existing ArtDirection without resending its markdown, which is a specific verb+resource action. It also distinguishes between save=false (draft) and save=true (update), and implies this is distinct from update_art_direction by emphasizing feedback-driven async revision.

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 guidance on the save parameter (false for draft, true for update with stale-edit protection) and notes System ArtDirections support drafts only. It also instructs to poll get_art_direction_authoring_job for the result. However, it does not explicitly name alternative tools or state when not to use this tool, so some inference is left to the agent.

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