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

Annotations only cover read-only and open-world status, and the description adds substantial behavior beyond that: per-site failures preserve successes, duplicate labels keep separate input-position identities, sort uses nulls-last with stable ties and rejects mismatched/unknown units, and oversized payloads stage completely with summaryDatasets/summaryIndex preserving ordered arrays. These are non-obvious traits an agent could not infer from any structured field.

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?

Purpose and scope are front-loaded in the first clause, followed by sorted behavioral detail with no filler sentences. The final sentence ('Oversized observations and summaries stage completely; summaryDatasets handles and summaryIndex preserve complete ordered summary arrays') is compressed to the point of being hard to parse on first read, which costs a point.

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 complex multi-branch schema (four temporalResolution variants, nested selection oneOf) with an output schema present, the description covers the compatibility rules, partial-failure semantics, sorting behavior, and staging outputs. Nothing an agent needs before calling is missing, and return values are correctly left to the output schema.

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 baseline is 3; the description earns above baseline by explaining what the sort parameter actually does (which means it uses, tie-breaking, unit-compatibility rule) and by explaining staging/canvas_id reuse. It does not re-explain the scalar fields already documented in the schema, which is appropriate.

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?

States a specific verb and resource — comparing 2–10 labeled coordinates with a shared parameter selection and window — plus the default resolution (climatology). The multi-site framing implicitly separates it from single-site siblings like nasa_power_get_timeseries and nasa_power_get_climatology, but no sibling is named explicitly.

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 2–10 location constraint and climatology default imply the intended usage, but the description never states when to pick this over nasa_power_get_timeseries, nasa_power_get_region, or nasa_power_dataframe_query, nor any exclusion conditions. Guidance is inferable rather than stated.

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