Clara — Personal Clean Air Planner

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

With no annotations, the description carries the full burden. It discloses output format ('returns structured advice with a plain-English summary, health context, and local intervention information') and provides a presentation directive ('Present the summary to users first'). It also mentions composability with Hermes. It does not detail edge cases or failure modes, but covers the main behavioral aspects.

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 well-structured and front-loaded. The opening sentence states the core purpose, followed by usage guidance, composition notes, and return-value info. The parameter list is thorough but each line is concise and informative. No wasted words.

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?

Given the 10-parameter complexity and no output schema, the description covers the essential context: purpose, usage triggers, parameter meanings, and return format. It lacks explicit guidance on parameter combinations (e.g., postcode vs. lat/long, required at least one) but otherwise provides a complete picture.

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?

The schema has 0% description coverage, but the description compensates richly by explaining every parameter: postcode, latitude/longitude, pm25/no2 overrides, setting, has_gas_cooker, commute_mode, has_indoor_sources, and audience. It also adds crucial context like 'provides coords + LAEI pollution' and 'affects indoor advice.'

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's purpose: 'Personalised air quality advice for a UK location and a specific user context.' It uses a specific verb and resource, and elaborates on composing location-specific pollution with user context. While it does not explicitly name sibling exposure_assessment, it differentiates by focusing on personalized, evidence-based advice rather than generic assessment.

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 provides explicit when-to-use guidance: 'Use this tool whenever the user asks an air-quality question that depends on *who they are* or *what they're about to do*' with clear examples. It does not offer explicit when-not-to-use or alternatives, but the context is so specific that exclusion is implied.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It covers key aspects: time-weighted modelling across environments, indoor source adjustments, route-based factors, and the annual-average limitation. It does not disclose return format or units, but it does state a major limitation ('not live readings') and explains the model's inputs. This is strong given the constraints.

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 structured as a summary paragraph followed by an Args list. Each sentence serves a purpose, and the front-loaded purpose statement is efficient. It is slightly longer than strictly necessary, but the param explanations are valuable and well-organized. No fluff or repetition.

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 tool has 8 parameters and no output schema, so the description should cover the return value to be fully complete. It clearly explains the estimation approach but does not state what the function returns (e.g., a numeric exposure value, units, or a breakdown). This is a notable gap for a complex computation tool, making it minimally viable but not complete.

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?

The description adds substantial meaning for every parameter, far beyond the bare schema titles. It explains each arg with domain context (e.g., 'smoking_at_home: Whether anyone smokes indoors (major PM2.5 source)'), provides example values (postcode format, tube line), and clarifies optionality. Since schema coverage is 0%, this description fully compensates.

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 opens with a clear, specific action: 'Estimate personal daily air pollution exposure across home, work, and commute.' This verb+resource pairing immediately defines the tool's purpose and differentiates it from the sibling 'contextual_advice', which likely provides recommendations rather than quantitative estimates.

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 provides clear usage context: it explains the methodology (time-weighted modelling) and explicitly notes it uses annual averages, not live readings. It gives per-parameter guidance (e.g., 'Omit if not commuting' for work_postcode), but does not explicitly state when to choose this tool over the sibling or name exclusions. This is clear context, though not full when/when-not guidance.

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