rca_narrate

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

The description is rich in behavioral detail (air-gapped, local model, only rephrases, never adds cause/number/citation, no device I/O), but it directly contradicts the annotation readOnlyHint: false. Since the description claims 'Read-only' while annotations indicate the opposite, this is a clear annotation contradiction, warranting the minimum score.

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 a clear functional summary, behavioral notes, Args, Returns, and an example. It is somewhat verbose but every sentence adds context (prerequisites, strict prompt, return shape). It is front-loaded with the primary purpose, making it easy to scan.

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 that this tool invokes a local LLM and there is no output schema, the description covers prerequisites (pip install, running model), behavioral constraints (no additions), input source (RCA verdict), parameters, return format, and an example. It also points to docs for the strict prompt, making it complete for an agent to invoke correctly.

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 0%, but the description fully compensates with a detailed Args section. It explains that 'verdict' is the output of downtime_root_cause, defines base_url as the Ollama server URL, lists model defaults, and notes provider currently only supports 'ollama'. This goes beyond the schema's property names and defaults, providing actionable semantics.

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 states a specific verb and resource: 'Narrate a cited RCA verdict in plain language via an on-box LLM.' This clearly distinguishes it from siblings like downtime_root_cause (which computes the verdict) by emphasizing the narration step. The READ tag and air-gapped note further clarify its unique role.

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 example explicitly links to downtime_root_cause output, and the phrase 'hands the already-computed, already-cited verdict' implies it should be used after a verdict exists. However, it does not explicitly state when NOT to use it or name alternative narration tools, so it stops short of full usage boundaries.

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