interpret_result

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

Beyond the readOnlyHint annotation, the description discloses rich behavioral traits: it REUSES the agent's own model without an API key when sampling is advertised, falls back to a deterministic structured brief otherwise, NEVER fabricates a narrative, and grounds every claim in the result's own numbers. It also flags the chaining prerequisite (result_id from an as_handle=true call), all of which materially shapes an agent's expectations.

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 front-loaded with the purpose and every sentence carries information. There is mild redundancy between 'it NEVER fabricates a narrative' and 'the model is told not to invent estimates' — two sentences making the same guarantee — but the overall density is high and well organized.

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?

For a tool with 8 parameters, an output schema, and dual-mode behavior, the description covers the essential workflow (chaining, sampling-dependent path, grounding guarantees) while leaving parameter-level detail to the fully documented schema. The detail-level token guidance lives in the schema where it belongs, so the division of labor is appropriate.

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 coverage is 100%, so the baseline is 3, but the description adds workflow semantics beyond the schema: it ties result_id to a specific earlier call mode (as_handle=true) and explains that question focuses the interpretation while audience tunes it. This connects the parameters to the calling pattern in a way the schema does not.

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 opens with a specific verb+resource ('Natural-language interpretation of a fitted result') and elaborates what the interpretation covers: the estimate, its uncertainty, and what the design does/does not identify. It is clearly distinct from plotting or diagnostic siblings in intent, though it never explicitly names a sibling (e.g., plot_from_result, brief_result) to differentiate from.

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 gives clear context for when and how to use the tool: pass a result_id from an earlier as_handle=true call, and it adapts its behavior based on whether the MCP client advertised sampling. It explains both operating modes (agent-model reuse vs deterministic fallback) but stops short of explicit when-not-to-use guidance or named alternatives among the 240+ siblings.

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