Workflow (write)

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

Goes well beyond the destructiveHint=true annotation by disclosing the overwrite risk, that every change is read back from Resolve, and the meaning of receipt.verified=false ('it did not take') — a verification contract an agent cannot infer from annotations alone. Also references dry_run/snapshot behavior (server policy when omitted) documented in the schema.

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-loads the most important warning (overwrite + verification) before the action list, and the bulleted op enumeration is scannable. Slightly redundant with the schema's per-action descriptions, but no padding sentences.

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 a 5-way discriminated union, full schema coverage, and an output schema, the description supplies enough to pick the right action and understand the write semantics. The only gap is the absence of any pointer on how this relates to recipe_run/describe_action for prebuilt or introspective workflows.

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 schema already documents op, dry_run, and snapshot, and the action blurbs in the description largely mirror the const-field descriptions in the schema. The description adds little parameter-level detail beyond what structured data provides, so the 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?

States the resource ('workflow state') and enumerates five concrete operations (apply_look, build_vertical_reel, conform_from_edl, deliver, title_overlay) with a specific verb for each. The umbrella verb 'change workflow state' is generic, but the action list makes it unambiguous what the tool actually does. It does not distinguish itself from recipe_run or describe_action, both of which plausibly overlap.

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 routes sequences and repeated changes to batch_run ('Calls known in advance ... ONE batch_run'), which is real when-to-use guidance. It also warns that it may overwrite current values, implicitly signaling this is for writes over a read tool. It gives no guidance on when to pick a workflow op versus the granular siblings (color_write, timeline_write, render_write).

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