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

With no annotations provided, the description carries the full burden of behavioral disclosure. It covers update cadence ('Built nightly over the trailing 30 days'), caching ('1h cache'), and the meaning of status values ('red/amber/green'). It also explains that the tool returns an interpretation string. It does not explicitly state that the tool is read-only, but given the telemetry nature, this is implicit and not a critical gap.

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 information-dense but well-structured: it starts with a one-sentence definition, then states the build frequency, then lists return fields with examples, and ends with actionable behavioral guidance. No sentence is redundant; the length is justified by the need to explain a telemetry tool with no output schema.

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?

Since there is no output schema, the description fully enumerates all return fields with meanings and example values ('stated_coverage', 'realised_coverage', 'coverage_delta', 'status', 'n_pairs', etc.). It also provides operational context (nightly build, 30-day window, cache) and an interpretation rule. For a parameterless tool, this is a complete and self-sufficient description.

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 zero parameters, so per the rubric the baseline is 4. The description does not need to explain parameters; it goes further by describing the output fields in detail, which is beyond the parameter dimension.

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's purpose: 'Live conformal-coverage telemetry: how often the model's stated 90% intervals actually contain the realised 5d returns.' This is a specific verb+resource (telemetry for model calibration) and distinguishes it from siblings like tengu_v3_accuracy or tengu_v3_believability by focusing on interval coverage. It also gives concrete metrics and sample numbers.

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 provides a clear usage directive: 'Treat status=red as a verdict-grade caveat — chat should attach "model intervals currently under-covering" to any ml_prediction citation when this returns red.' This tells the agent when and how to act on the result. However, it does not explicitly mention when not to use this tool or compare alternatives among the many sibling tools, so it misses the full 'when/when-not/alternatives' guidance.

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