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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses that corrections are returned separately, that 'nothing is applied silently', that corrections appear only after multiple observations agree, that implausible values are set aside rather than averaged, and that the source reports are returned. It does not mention authentication, rate limits, or explicit side effects (beyond billing via npub, which is in the schema), but the provided behavioral notes are meaningful and non-obvious.

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 and front-loaded: a one-sentence summary, a paragraph of context, a paragraph on return values, and a paragraph on behavioral principles. Each sentence serves a purpose: distinguishing the tool, explaining outputs, and setting expectations about safety and consensus. No wasted or redundant wording.

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, the presence of an output schema, and the rich input schema, the description covers the essential operational and behavioral aspects an agent needs. It explains the output structure at a high level, the consensus requirement, and the fact that reports are returned. It does not explicitly state prerequisites like 'block must be saved first', but the input schema already handles that. Overall, it is sufficiently complete for correct invocation and selection.

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 83%, so the schema already documents the parameters well; the baseline is 3. The description adds conceptual context about why observations matter (measuring the gap left by the grid model) and what the two corrections respectively address, but it does not add detailed parameter-level semantics beyond what the schema already states. It is adequate but not compensating for any schema gap.

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 a specific action ('Turn a block's own field reports into a correction on the model') and distinguishes this tool from all siblings by contrasting it with the 9 km grid used by 'every other tool here.' The return of two distinct corrections (heat bias and days bias) further clarifies its unique purpose. An agent can easily tell this is the tool for farm-specific calibration rather than grid-based estimates.

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 strong contextual guidance by explaining that other tools rely on a coarse grid and cannot capture local features (hedgerow, pond, cold-air outlet), and that this tool's observations measure that gap. This implies when to use the tool, but it stops short of explicitly naming alternative tools or stating 'use X instead when Y'. The guidance is clear enough for an agent to infer the appropriate scenario.

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