Overwing

Evaluate many texts

evaluate_batch

Score up to 50 texts against one rule set in a single call. Each item counts as one evaluation. Returns a summary plus per-item verdicts; items can fail independently. Needs an organization key.

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": {
      "items": "<items>"
    },
    "name": "evaluate_batch"
  }
}

Input Schema

Name	Required	Description	Default
`items`	Yes
`store`	No	False runs every item without keeping its input text or context
`context`	No	Facts the rules may reference: recipient, channel, whether you own the data, sender, purpose. Sent to the model alongside the text (max 8 KB). Use the 'outbound-message' rule set to have it honoured.
`rule_set`	No		content-safety

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 30, 2026

TDQS

A3.7/5.0

Behavior4/5

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

With readOnlyHint=false signalling a write/quota-consuming operation, the description adds genuine context beyond the annotation: per-item billing ('Each item counts as one evaluation'), partial-failure semantics ('items can fail independently'), and an auth prerequisite ('Needs an organization key'). It still omits whether evaluations persist by default (the 'store' flag), which is a meaningful behavioral trait left to the schema.

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?

Three short sentences, front-loaded with the scale and batching constraint, each carrying distinct information (scale, quota, return/failure shape, auth). No filler, though 'Returns a summary plus per-item verdicts' and 'items can fail independently' are partially redundant with each other.

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

Completeness4/5

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

There is no output schema, so the description correctly covers the return shape and partial-failure behavior, and flags the auth requirement for a 4-parameter nested-object tool. The main remaining gap is behavioral detail around the 'store' default and how batch-level versus per-item context interact, which the schema only partly explains.

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

Parameters3/5

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

Schema coverage is 50%, so half the parameters get only schema-level documentation. The description reinforces 'rule set' and the item-count ceiling, and 'organization key' is an auth note rather than a parameter (there is no such parameter in the schema). 'store' and the batch-level 'context' interplay are not addressed in prose, so it does not fully compensate for the coverage gap; baseline 3 applies.

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 (Score) and resource (texts) with an explicit scale bound (up to 50) and batching constraint ('in a single call'). This implicitly distinguishes it from the sibling 'evaluate' (single-item), though it never names that sibling, which keeps it short of a 5.

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 batch framing and the quota note ('Each item counts as one evaluation'), giving an agent a cost signal for choosing this over repeated 'evaluate' calls. However, there is no explicit when-to-use/when-not guidance or named alternative, so it remains implied rather than stated.

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

All Overwing tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.