plan_research

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

Annotations already declare readOnlyHint=true, so the description's 'without executing it' aligns with that. Beyond annotations, it adds that the tool returns JSON with sub-questions, recommended sources, and cost estimates, and explains the workflow of passing the result to 'research'. This adds meaningful behavioral context without contradicting the annotations.

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 four sentences with no filler. The primary purpose is stated first, followed by the return value, the usage scenario, and the follow-up action. Each sentence earns its place and the structure is front-loaded for quick comprehension.

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?

The tool is read-only, has a simple two-parameter schema, and an output schema exists, so the description doesn't need to detail the return structure. It explains the full workflow (plan → review → execute with 'research') and is consistent with the sibling tool set. Nothing essential 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% – both 'question' and 'depth' have descriptions, and 'depth' includes enumerations. The tool description does not introduce any additional parameter semantics beyond that, so it meets the baseline for a fully described schema. It does add a hint that the question should be 'complex', but that's not a parameter-level detail.

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 names a specific verb ('Build'), a clear resource ('structured research plan'), and explicitly states it does NOT execute the research. It contrasts with siblings like 'research' by noting it returns a plan for review, differentiating it unambiguously.

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 explicitly states when to use it ('when you want to review or edit the plan before committing') and implicitly when not to use it (when you want execution) by directing the agent to pass the returned JSON to the 'research' tool. This provides clear routing to the correct sibling.

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