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

Annotations already cover the safety profile (readOnly true, destructive false, openWorld false), so the bar is lower; the description still adds real behavioral context — the value space for each row (state, flow, acceleration), the CSV-per-day granularity, and the access-scoped depth constraint. The closing caveat that readings are measurements, not predictions or recommendations, further clarifies semantics.

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?

Front-loaded with purpose and output format, then access constraints, then the semantic caveat. The parenthetical enumeration of state values is dense but informative; the whole thing is three sentences with minimal waste.

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?

With an output schema present, return values needn't be explained, yet the description usefully characterizes the CSV layout and field domains. Combined with the access-depth pointer to list_datasets and the annotations covering safety, the definition is nearly complete; only the sibling routing is missing.

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 100%, so the schema already documents dataset, date_start, and date_end with patterns, defaults, and inclusivity. The description only restates the window concept and access depth, adding no new syntax or format detail beyond the schema. Baseline 3 applies.

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 states a specific verb and resource ('Daily pressure for a window') plus the output shape ('compact CSV, one row per day'), so an agent knows exactly what it returns. It does not, however, name or distinguish itself from the obvious sibling get_latest_pressure, which differs only by scope.

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?

There is implied usage — it serves the window of days your access includes — and it points to list_datasets for determining depth, which is a useful prerequisite hint. But it never states when to prefer this over get_latest_pressure or fetch, and gives no explicit exclusions.

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