rca_dtree_start

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

The description discloses that the tool returns the first question and expects subsequent answers via rca_dtree_answer, and outlines the return structure. However, it does not mention side effects (e.g., session creation), required authentication (token parameter), or any mutability assumptions beyond what annotations (all false) imply. Annotations are uninformative, so description partially carries the burden.

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 with clear sections (modes, args, returns) and uses emoji for quick scanning. It is front-loaded with the core purpose. Some redundancy exists (e.g., parameter list mirrors schema), but overall it is efficient and earns its length.

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 complexity (two modes, nested parameters, interactive workflow) and the presence of an output schema (though not shown), the description covers essential aspects: purpose, modes, parameter roles, and return format. Minor gaps include missing details on token authentication and potential limitations (e.g., session expiration).

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 description adds meaning beyond the input schema by explaining the two modes and the relationship between guide_id and fmea_result_id. The schema itself contains property descriptions (e.g., token, symptom, client_id), but the description ties them together functionally. However, it does not elaborate on all parameters (e.g., equipment_id, symptom format).

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 that the tool begins an interactive diagnostic session using a decision tree guide. It specifies the resource (diagnostic session) and action (start), and distinguishes from siblings like rca_dtree_answer (which answers) and rca_dtree_list_sessions (which lists sessions) by focusing on session initiation.

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 two distinct modes (specific guide_id vs 'auto' from FMEA) and their prerequisites (e.g., fmea_result_id needed for auto mode). While it does not explicitly state when to avoid this tool or list alternative tools, the context for using each mode is clear.

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