Refine Plan

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

Annotations are minimal (only title), so the description must disclose behavioral traits. It mentions inputs and purpose but does not specify whether the tool mutates the plan or returns a new one, nor any side effects or safety concerns.

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?

The description is well-organized with a brief definition, a 'When to use' list, and an 'Input' list. Every sentence is substantive and front-loaded.

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 no output schema, the description should explain what the tool returns. It does not mention return value or behavior when refinement succeeds or fails. The tool also assumes a pre-existing plan but doesn't explicitly state prerequisites.

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 baseline is 3. The description adds some context (e.g., 'JSON from previous create_plan call') but largely mirrors the schema.

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 explicitly states the tool refines an implementation plan based on feedback or clarifications. It provides specific use cases, distinguishing it from other plan tools like delete_plan or load_plan.

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 tool clearly enumerates when to use it (after reviewing, to answer questions, add detail, change approach). It doesn't explicitly say when not to use it, but the context is sufficient for an AI agent.

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