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

Adds substantial context beyond the annotations: a fixed 10-credit cost charged once per proposal, a required API key, bootstrap instructions, and how gaps are reported. These are the exact behavioral facts an agent needs before spending money, and none of them conflict with the declared hints (non-read-only, non-idempotent, non-destructive).

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 purpose and output shape before behavior, cost, and auth, so the important content is read first. The auth bootstrap URL plus sample JSON payload is slightly heavy for a tool description, but each part does serve a real prerequisite.

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 an output schema, this description is fully sufficient: it covers cost, prerequisites, persistence side effects, failure/degradation semantics, and the handoff to workflow_run. An agent could invoke it correctly without any further information.

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%, so baseline is 3, but the description adds real meaning: 'save: true to keep it on the account, after which workflow_run can run it by the returned id,' which conveys the downstream consequence rather than just the boolean flag. The goal semantics are largely left to the schema, keeping it short of a 5.

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 and resource ('Describe a job... get back a workflow') and names what the output contains: a name, inputs, and ordered steps with rationale. It is clearly distinguished from the sibling workflow_run, which is described as the consumer of a saved proposal rather than a generator.

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?

Explains the two operating modes well: default returns a proposal for reading, while save: true persists it so workflow_run can execute it by id. It also tells the agent what happens when no tool fits (partial=true, missing names the gap). It does not contrast with workflow_list, but the primary when-to-use decision is covered.

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