step_plan

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

Annotations establish the mutation/safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=true); the description adds meaningful context beyond them — that nothing is executed on submit and that the plan is released manually via the panel or step_control. It omits whether re-submission or cancellation is possible.

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?

Three short, front-loaded lines with no filler; the core behavior leads and the mechanical detail follows. The trailing reference line is functional but slightly boilerplate.

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 described. However, for a non-read-only plan-submission tool with three parameters at 0% schema coverage, the description leaves doc_name semantics and the fate/lifecycle of a submitted plan unexplained.

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 0%, so the description carries the burden. It clarifies that each element of 'steps' is a cad() argument dict, which is valuable, but says nothing about doc_name or the optional description field.

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 (submit) plus resource (modeling plan to the document's step journal) and immediately adds the key scope qualifier 'without executing it'. This separates it from cad/execute_code, though it does not name those siblings directly.

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?

The description implies usage by explaining what happens after submission ('waits for release in the CADPilot Steps panel or via step_control'), but never states when to choose step_plan over cad or when not to use it. Usage is inferable, not explicit.

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