DECIDE. Head-to-head comparison of exactly two options with per-criterion win counts and margin. Pass option_a/option_b (or a 2-element options array), criteria, and scores.
| Name | Required | Description | Default |
|---|---|---|---|
| method | No | ||
| scores | Yes | ||
| options | No | ||
| criteria | Yes | ||
| option_a | No | ||
| option_b | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does disclose the output nature ('per-criterion win counts and margin') and input constraints. It does not state whether the operation is read-only, or how edge cases (e.g., both option_a and options provided) are handled, so it's only partially transparent.
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 two sentences, front-loaded with the core purpose and followed by input instructions. No unnecessary words; the 'DECIDE.' prefix is a brand tag but harmless.
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 essential input-output concept but lacks detail on the scores structure, the meaning of 'margin,' and the method parameter. Since there is no output schema and no annotations, these gaps could lead to incorrect invocation.
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 clarifies that options can be provided as two separate strings or a 2-element array, and it names criteria and scores as required. However, it omits the 'method' parameter entirely and does not explain the structure of the 'scores' object, leaving significant semantic gaps given 0% schema coverage.
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 uses a specific verb ('comparison') and resource ('exactly two options'), and it differentiates from sibling tools like 'decide' by emphasizing the head-to-head pairing and the per-criterion win counts/margin output. This makes the tool's purpose clear and distinct.
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 clearly states the tool's scope ('exactly two options') and how to supply inputs ('Pass option_a/option_b (or a 2-element options array), criteria, and scores'), giving the agent a clear when-to-use condition. It does not name alternative tools for other cases, but the specificity of comparing two options is sufficient.
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.
Most tools have clear, distinct purposes across three namespaces (calc_, decide_, sim_) plus composites. Some conceptual overlap exists (e.g., decide_sensitivity vs. sim_sensitivity, decide_score vs. decide), but descriptions clarify the boundaries well.
Names follow a consistent snake_case convention with a namespace prefix (calc_, decide_, sim_) and a descriptive verb_noun structure. Even composite tools and utilities like health_check and list_capabilities fit the pattern.
24 tools is on the heavier side, but it's justified for a meta-server exposing three distinct engines plus cross-domain composites. The count is appropriately scoped for the breadth of capabilities advertised.
The set covers all core domains with discovery (list_capabilities, *_list_*), health_check, and composite tools linking simulation to decision and valuation. Minor gaps include lack of a template management tool, but sim_run accepts free-form models, mitigating this.