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

Annotations already carry readOnlyHint/openWorldHint/idempotentHint, lowering the burden. The description adds genuinely valuable non-obvious behavior beyond that: the DataCanvas spill mechanism (preview + canvasId + table name), internal paging up to a spill threshold, and the explicit unit non-conversion ('the server never converts between µg/m³, ppm, and ppb'). These give the agent actionable expectations not visible in annotations. It doesn't specify the exact spill threshold, a minor gap.

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?

Single dense paragraph, front-loaded with purpose before mechanics. Every sentence earns its place: use case, spill behavior, unit handling, and aggregation tradeoffs. Slightly run-on with semicolon/colon chains, but efficient overall and avoids redundancy with the schema.

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 7-parameter tool with an output schema, the description is strong: it covers the spill path (critical for large ranges), unit semantics, aggregation choice tradeoffs, and references openaq_find_locations/openaq_dataframe_query for id sourcing and follow-up. Since an output schema exists, return values need no explanation. Minor omissions are the exact spill threshold and explicit differentiation from get_readings.

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 every parameter thoroughly (datetime formats, defaults, limits, source of ids). The description adds some value — the per-bucket statistical summary composition (min, median, max, mean, sd) for hourly/daily aggregation, and the conceptual pairing of locationId+parametersId — but these are marginal additions over an already-rich schema.

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 — 'Historical measurement series for one pollutant at one station over a date range' — and immediately gives the intended use cases ('trend analysis', 'was last week worse than the monthly average?'). The single-pollutant, single-station scope distinguishes it from broader siblings like get_readings, and the DataCanvas spill explicitly ties it to openaq_dataframe_query.

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 clear selection context: 'work in stations', trend-focused use, and concrete aggregation guidance ('Use "daily" for multi-month trends... "raw" for fine-grained recent analysis'). It also names openaq_dataframe_query as the follow-up when results spill. However, it never explicitly says when NOT to use this tool versus the sibling openaq_get_readings, so the routing guidance stops short of full exclusions.

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