Create or save a workflow plan

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

Annotations only say this is a non-read-only, non-destructive call. The description goes well beyond that: no charge and no run started, a hard 256000-byte bound on the document, strict schema enforcement, exact-narration preservation, and a concrete lost-answer recovery procedure (read and compare rather than blindly re-save). That is unusually rich behavioral disclosure for a write-style tool.

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?

Five short sentences, front-loaded with purpose, then the parameter branch rule, then constraints, then the failure-recovery note. No sentence is redundant and none restates the name or annotations.

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 tool with a very deep nested schema, no output schema and no annotation detail, the description covers the economically important facts (free, no run, size bound, revision protocol, save-recovery). The one gap is that it never says what a successful call yields (e.g. a plan id or version) nor which call to use to compare the saved document, which matters given there is no output schema.

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?

Top-level schema coverage is 0%, so the description carries the load — and it does for two of three parameters, defining the create-vs-revision meaning of the plan_id/base_version pairing that the raw 'string pattern' and 'integer' schema does not. The document parameter is handled only as 'complete' plus a size bound, though its internal structure is described by the schema itself.

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 pair and resource ('Create or save a workflow plan') and immediately scopes it against the paying/running siblings with 'without paying or starting a run'. An agent can distinguish this from quote_workflow_plan, approve_workflow_plan and run_workflow_plan without opening any 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 an explicit branch rule — 'Omit both plan_id and base_version to create; supply both to save a revision' — and a when-not caution ('do not automatically approve or purchase'). It stops short of naming the sibling tools that handle approval and purchase, so routing is implied rather than spelled out.

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