brain_plan

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

The description explicitly declares the tool as READ-ONLY with no side effects, no writes, and no external network calls. Since no annotations are provided, the description carries the full burden and excels by being upfront about the safety profile. It also clarifies what the return value contains (failure modes, concrete steps, checklist) and requires a valid instance_id, giving full behavioral transparency.

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-structured and front-loaded with the critical READ-ONLY label. It packs significant information into a concise paragraph with clear sections: safety declaration, purpose, examples, output structure, and usage guidance. Every sentence adds value, and there is no repetition or filler.

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 the tool's moderate complexity (3 parameters, 100% schema coverage, no output schema, no annotations), the description provides complete context: it explains the tool's role, input requirements, output structure, and usage timing. The presence of sibling tools like brain_predict increases the need for differentiation, which the description handles well. No gaps remain.

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 value by explaining the role of each parameter: it mentions 'requires a valid instance_id' and gives example values for the task parameter ('upgrade Postgres 14→16', 'add Stripe webhooks'). However, it does not explicitly describe the top_k parameter's behavior beyond what the schema provides, which prevents a perfect score.

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 starts with a clear READ-ONLY label and then provides a detailed verb+resource definition: 'Generative planning layer on top of the CKG' that returns an ordered action plan. It explicitly contrasts with brain_predict by stating 'brain_plan answers what should I do, in what order?', which effectively distinguishes it from sibling tools. The purpose is specific and unambiguous.

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 explicitly states when to use the tool: 'Call before starting non-trivial work.' It also provides a clear when-not-to-use alternative by contrasting with brain_predict, and lists example tasks ('upgrade Postgres 14→16', 'add Stripe webhooks'). This gives the agent strong guidance on invocation context and alternatives.

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