pvsyst_inspect_weather_csv

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

No annotations exist, so the description carries the full burden and does so well: it declares read-only behavior, enumerates exactly what is reported (metadata/units, gaps, duplicates, bad numbers, monthly irradiation/temperature, SHA-256), and states hard input constraints (GHI/Tamb required, whole-year 00:00..23:00 including leap day, no silent filling or time conversion). It does not say how a non-conforming CSV surfaces (error vs. findings payload), which keeps it below a 5.

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 read-only nature are front-loaded, then constraints, then validity scope; nearly every sentence carries information. It is dense but not padded, with only minor redundancy between the whole-year timestamp rule and the 'valid covers this CSV profile only' caveat.

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?

Behaviorally rich for a no-annotation, no-output-schema tool, but an agent still cannot determine what the two arguments mean or how results/failures are returned. Adequate to decide whether to call it, incomplete for calling it 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% for both parameters and the description never mentions them. 'csv_name' is left ambiguous (bare filename vs. path/location) and 'expected_year' is never explained at all, despite the whole-year requirement implying its role. With zero schema documentation, this is a material gap the description needed to close.

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 ('Check a PVsyst standard hourly CSV in Meteo') plus the moment of use ('before preparing a full-year run'). It also draws an explicit scope boundary against sibling concerns ('not MEF/SIT matching or native MET correctness'), so an agent can separate it from review_weather/prepare_weather without opening the schema.

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?

Gives clear when-to-use ('before preparing a full-year run') and when-not ('valid covers this CSV profile only, not MEF/SIT matching or native MET correctness'), plus a routing hint that POA/time-reference cases 'need separate review'. What it lacks is naming the actual alternative tools an agent should call instead.

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