field_stats

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds a genuine behavioral detail: it reads directly from ASCII field files, hinting that binary-format cases may not work — useful context the schema does not convey, though return format and failure modes remain unstated.

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?

A single dense sentence with the operation front-loaded before the qualifiers. Efficient, though the parenthetical about internal/per-patch breaks the flow slightly.

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 simple read-only metric tool with no output schema, saying it returns min/max/mean covers the essentials, and the ASCII-file note is a nice addition. It is adequate but leaves gaps around output shape, units, and what happens for non-ASCII or missing fields.

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 75% and the case/time/field params are reasonably documented in the schema itself. The description adds 'internal and per patch' (mapping loosely to the undocumented region parameter) and the time-scoping constraint, but says nothing about case paths or region semantics beyond what the schema provides.

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 (computes min/max/mean) and resource (a field's values, internal and per patch) at a given time. Clear enough to separate from siblings like case_summary or post_process, though it never names those alternatives 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 phrase 'at a time' implies the tool is for point-in-time sampling rather than time-series analysis, but there is no explicit when-to-use guidance and no mention of alternative tools (post_process, case_summary, solver_progress) an agent should consider instead.

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