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

Annotations already declare read-only, idempotent, non-destructive, open-world, so the description goes further and adds the traits that actually matter: only the latest 100 hourly rows are returned while aggregates span the full period, data are provisional rather than the ratified archive, and the call costs 1 credit. That truncation rule plus the data-quality caveat is exactly the kind of behavior an agent cannot get from annotations.

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 the core contract (what is returned and how much), then scope, then caveats and cost — good ordering. The persona list ('councillors, campaigners, schools, journalists and researchers') is slightly padded, but the rest is dense and earns its place.

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?

There is no output schema, so the description carries the burden of describing the response, and it does: the row cap, which statistics are computed over the whole period (min, max, mean, peak hour, daily means), and the provisional-data caveat. An agent could decide and call correctly on this alone.

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 baseline is 3. The description does reinforce the either/or nature of timeseries_id vs station_id and the 1–168 hour window, but it adds no format, default, or edge-case detail beyond what the schema fields already state.

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?

Opens with a concrete verb-and-resource statement: hourly readings of one pollutant at one Defra UK-AIR monitor over 1–168 hours. It is clearly distinguishable from the sibling current-level tools (no2_level_near, pm25_level_near, air_quality_index_near) by being explicitly historical, and it names where the identifier comes from.

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 a concrete use context ('when was pollution highest this week' for councillors, campaigners, journalists) and points at the other air quality tools as the source of the timeseries_id/station_id. It stops short of an explicit 'use this instead of X when…' exclusion against the current-level siblings, but the historical framing makes the split inferable.

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