refine_plan

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description usefully adds that the operation is non-destructive: it returns a new plan id and leaves the original intact. It does not mention validation failure modes (e.g. incompatible overrides) or any cost, but the key mutation semantics are disclosed.

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?

Two tight sentences with zero waste, and the return/immutability fact is front-loaded alongside the purpose.

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 no elaboration, and the description still notes that a new plan id is returned. For a tool whose override semantics live in the schema, this is nearly complete; only guidance on choosing between refine_plan and plan is missing.

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% and the $defs go into deep detail on each override, including null/omitted semantics, so the schema carries the burden. The description adds nothing parameter-specific beyond the example in the schema itself; 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 a specific verb+resource+scope: building a new plan derived from an existing one by changing decisions. This implicitly separates it from the `plan` sibling (which builds from scratch), though no sibling is named explicitly.

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?

Usage is only implied by 'from an existing one' — the agent can infer this is the tool for modifying an already-created plan rather than creating a fresh one, but there is no explicit when-to-use/when-not guidance or reference to `plan`/`forecast` alternatives.

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