Skip to main content
Glama
Sign In
daf-jev

daf-jev

by docxology
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

jev_evaluate

Evaluate a fixed question set across many states concurrently to return aggregate metrics such as token totals, mean and p95 latency, and error counts.

Instructions

Evaluate a fixed question set over many states, concurrently.

Returns the aggregate summary only (no per-state records): {n_states, n_errors, total_input_tokens, total_output_tokens, mean_latency_s, p95_latency_s, questions}. Raises ValueError on an empty states list or a state that is neither a string nor a JSON object/array. provider selects the registered API provider (default jev).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "states": "<states>",
      "questions": "<questions>"
    },
    "name": "jev_evaluate"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo
statesYes
providerNojev
questionsYes
concurrencyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.2

TDQS

B3.2/5.0
Behavior3/5

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

With zero annotations, the description carries the full burden and does deliver real value: it names the exact aggregate return shape (n_states, n_errors, token totals, mean/p95 latency, questions) and the two ValueError conditions (empty states list, state that is neither string nor object/array). It still omits whether calls hit an external paid API, how partial failures are counted into n_errors, and whether concurrency has limits — meaningful gaps for a network-bound batch operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Core behavior is front-loaded in the first sentence, followed by a compact formatted return shape and a short error/default note — no filler sentences. The literal docstring-style backtick formatting is slightly noisy but the information density is high and each sentence adds something.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter tool with nested objects, no output schema, and no annotations, the description compensates well on the return side by enumerating the aggregate payload and error cases. It remains incomplete on the input side: the structure of `questions`, the effect of `model` and `concurrency`, and the required-versus-optional contract are not addressed, which is a substantive gap for an agent composing a call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across five parameters, including a nested `questions` object whose key/value shape is completely undefined, so the description must compensate and largely does not. It covers only `provider` (registered API provider, default `jev`) and the accepted types of `states` via the error note; `model`, `concurrency`, and the entire `questions` structure get no explanation of meaning, format, or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — "Evaluate a fixed question set over many states, concurrently" — which pins down both the unit of work (question set) and the batching dimension (many states). It does not name or distinguish itself from likely siblings such as jev_ask, but the concurrent multi-state scope is clear enough to infer the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the phrase "over many states, concurrently," which signals this is the batch counterpart to a single-shot ask. However, there is no explicit when-to-use or when-not-to-use guidance, no mention of an alternative sibling, and no stated cost/concurrency tradeoff that would help an agent choose between this and a single evaluation call.

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

Deploy Server

Other Tools