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

With no annotations, the description carries the full burden. It discloses the return structure (narrative, data, summary) and gives a specific behavioral instruction: 'Present the narrative to users first.' It also explains that either location or site_code is required. It doesn't mention limitations like data gaps or authentication, but for a read-only historical data tool, the provided behavior is sufficient.

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?

The description is front-loaded with a clear one-sentence purpose, followed by the output structure and a terse but complete parameter list. Every sentence earns its place; no redundant or filler content. The structure is logical and easy to scan.

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?

The description covers the core purpose, output, and all parameters, and no output schema exists, so explaining return values is necessary and done adequately. It lacks details on the exact shape of the raw 'data' or 'summary' fields and doesn't clarify behavior if both location and site_code are given, but these are minor gaps given the tool's complexity.

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%, but the description compensates fully with an 'Args' section that explains each parameter: ISO format for dates, the 'location or site_code' alternative, optional pollutants with an example, and the frequency options with default. This goes far beyond the schema's bare types and defaults, adding critical meaning.

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 clearly states the tool retrieves historical air quality data for a site or location and includes health context. It distinguishes itself from siblings like get_current_aq by specifying 'historical' and adds a unique output (narrative with WHO guideline comparisons). The verb 'Get' and the resource are specific and non-tautological.

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 makes it evident this is for historical data (vs current), and the mention of health context and narrative implies use when users need plain-English interpretations. However, it does not explicitly state when not to use this tool or mention alternative tools like trend_analysis or get_aqi_summary, so it lacks explicit exclusions but provides clear context.

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