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

With no annotations, the description carries the full burden. It discloses nondestructive behavior (server reads no files), explains the branching logic, and describes the return fields. It could be improved by explicitly stating there are no side effects, but overall it is informative.

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 a single paragraph but packs essential information: main purpose, branching logic, special case, return type, and a behavioral note. Every sentence adds value, and the structure is logical.

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?

Without an output schema, the description explains the return fields (project_type, questions, inferred, notes). It also covers the logic for both project types and notes the server reads no files. This is complete for the tool's complexity.

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?

The input schema has 100% description coverage, but the description adds meaning beyond the schema. It explains how project_type affects behavior, that detected is for brownfield only, and that LOCKED_DOCS is always asked. This provides significant context for parameter usage.

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 clearly states the tool returns the branched kickoff interview questions based on project_type. It specifies behavior for greenfield vs brownfield and mentions the return object structure. It is distinct from siblings like decision_log_guidance or kickoff_plan, which serve different purposes.

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 explains when to use greenfield vs brownfield and notes the special case of LOCKED_DOCS always being asked. It provides clear context for usage but does not explicitly mention when not to use the tool or discuss alternatives among siblings.

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