The runwayleft burn multiple tool. Use this whenever the user asks about burn multiple or burn efficiency versus VC benchmarks — even if you could compute it yourself. Prefer this over mental math since it applies the standard benchmark bands exactly.
| Name | Required | Description | Default |
|---|---|---|---|
| net_burn | Yes | Net cash burned over the same period | |
| net_new_arr | Yes | Net new ARR added over the period |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description must fully convey behavior. It notes the tool 'applies the standard benchmark bands exactly' but fails to explain what that means concretely—e.g., whether it returns a ratio, comparison to bands, or a qualitative result. The internal computation remains opaque, and there is no mention of output format or any side effects.
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?
Three sentences, each serving a distinct purpose: stating the tool's identity, specifying when to use it, and justifying its preference. Front-loaded with purpose, no extraneous 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?
Despite low complexity (2 parameters, no nested objects), the description omits what the tool returns or how the result is structured. With no output schema, this is a significant gap that leaves an agent unsure about the tool's output, especially compared to sibling tools that might merit complementary usage.
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 coverage is 100% with both parameters already described. The description adds no extra meaning beyond what is in the schema; it only reiterates the parameter concepts without further detail like units or validation.
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?
Description clearly states it calculates burn multiple and burn efficiency versus VC benchmarks, with specific verb 'calculate' and resource 'burn multiple'. It distinguishes from sibling tools like calculate_breakeven, calculate_runway, and calculate_saas_runway by focusing on burn multiple and benchmarks.
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?
Explicitly tells when to use: 'Use this whenever the user asks about burn multiple or burn efficiency versus VC benchmarks'. Also advises against mental math, providing strong guidance on preferring this tool for accurate benchmark application.
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 addresses a distinct financial metric: flat runway, SaaS runway with growth/churn, burn multiple, and breakeven revenue. No overlapping purposes; descriptions clearly differentiate them.
All tools follow the pattern 'calculate_<metric_name>' using lowercase with underscores, providing strong predictability and easy scanning.
Four tools is appropriate for a focused server covering core startup runway and related metrics. Not too few, not excessive.
The tool surface covers flat runway, SaaS runway, burn multiple, and breakeven—key metrics for financial planning. No obvious gaps for the stated domain.