Business travel emissions (Scope 3 Cat 6), distance method: emissions = km × passengers × factor. Air factors come in with_rf / without_rf (radiative forcing) variants. Find factors via search_factors (section "business_travel").
| Name | Required | Description | Default |
|---|---|---|---|
| distance | Yes | { "value": <number>, "unit": "km|mi" }. | |
| factor_key | Yes | Per-passenger-km travel factor key. | |
| passengers | No | Optional, defaults to 1. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It discloses the calculation formula, unit flexibility (km/mi via distance object), and radiational forcing variants. Does not cover output format or edge cases, but sufficient for a pure calculation tool.
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?
Two efficient sentences: the first states purpose and formula, the second gives factor sourcing guidance. No wasted words, front-loaded with the most critical information.
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 calculation method, factor usage, and unit flexibility, which is adequate for a simple calculator. It does not explicitly state the return value format, but that is inferable from the formula and tool nature.
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 already covers all parameters with descriptions (100% coverage). The description adds value by explaining the formula and clarifying that factor_key is per-passenger-km with RF variants, going beyond the schema's minimal description.
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 function: calculating business travel emissions (Scope 3 Cat 6) using the distance method, with an explicit formula. This distinguishes it from sibling calculate_* tools that handle other emission categories.
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?
Provides explicit guidance on how to obtain factor keys via search_factors and notes the with_rf/without_rf variant distinction. Does not explicitly contrast with other calculate tools, but the name and context make the use case clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct role: search, lookup single, lookup batch, resolution, absence explanation, and separate calculation methods for distinct scopes. Even the discovery tools can be told apart by whether the input is a key, text, natural language, or a purpose. Domain calculators are cleanly separated by type of activity, so an agent should not confuse them.
All tools follow a consistent verb_nonn pattern: calculate_*, lookup_factor(s), search_factors, resolve_factor, explain_absence. The naming clearly signals both action and object, and even the singular/plur lookup distinction matches the batch versus single-key semantic.
Twelve tools is well-sopened for a broad emissons-factor API: six calculators, four discovery/lookup/resolution tools, one batch lookup, and one edge-case explainer. Each tool appears to serve a necessary purpose rather than adding redundant surface area.
The set covers the full workflow: discover factors, resolve amiguous plain-language queries, look them up individually or in batch, perform domain-relevant calculations, and even explain why a factor is absent. The main GHG scopes are covered by dedicated calculators while the generic calculate_activity fills gaps for any other factor data.
