eDiscovery Decoder News/Calc

Calculate Elusion

calculate_elusion

Read-onlyIdempotent

Estimate how much responsive/relevant material may remain in a set you chose NOT to review (the discard, null, or 'elusion' set). Use when a random sample of that excluded set has been coded — e.g. 'we sampled 400 culled docs and found 2 relevant.' Returns the elusion rate and a Wilson confidence interval. For an overall recall % from the same sample, use calculate_tar_recall_estimate. Aggregate counts only; not legal advice.

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": {
      "relevant_found_in_sample": "<relevant_found_in_sample>",
      "sample_size": "<sample_size>"
    },
    "name": "calculate_elusion"
  }
}

Input Schema

Name	Required	Description	Default
`sample_size`	Yes
`confidence_level`	No
`relevant_found_in_sample`	Yes

Output Schema

Name	Required	Description	Default
`formula`	Yes
`assumptions`	Yes
`elusion_rate`	Yes
`confidence_interval`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 7, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- addedInput schema / properties / relevant_found_in_sample / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / sample_size / maximum
```
Added value: +9007199254740991
```
First observedJun 23, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare this as a read-only, idempotent, closed-world calculation, so the safety profile is covered. The description adds value beyond them by stating the outputs (elusion rate plus a Wilson confidence interval), the aggregate-counts-only constraint, and the not-legal-advice caveat. It does not address edge cases such as a sample with zero relevant documents or invalid inputs, which keeps it below a 5.

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?

Four sentences, front-loaded with the core definition, with the sample-coded precondition and the sibling-tool routing following in priority order. Every sentence carries content, including the parenthetical synonyms that disambiguate domain terminology. The closing 'Aggregate counts only; not legal advice' is boilerplate but serves a real compliance purpose, so it earns its place.

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?

For a three-parameter statistical calculator with an output schema, the description covers purpose, precondition, example, output shape, and the alternative tool. The remaining gap is the undocumented confidence_level parameter and the absence of any note on behavior when the sample yields zero relevant documents — minor for a pure computation, but not complete.

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 description coverage is 0%, so the description carries the burden, and it only partially does so: the example implicitly maps sample_size to 'sampled 400' and relevant_found_in_sample to 'found 2 relevant'. The third parameter, confidence_level (default 0.95), is never mentioned in the description and is undocumented in the schema, leaving one of three parameters without semantic guidance.

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

Purpose5/5

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

The description names a specific verb and resource — estimate the elusion rate for a set that was excluded from review — and immediately defines the jargon ('the discard, null, or "elusion" set'). It explicitly contrasts itself with the sibling calculate_tar_recall_estimate, so an agent can route between the two without opening either schema.

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

Usage Guidelines5/5

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

It gives a concrete precondition ('use when a random sample of that excluded set has been coded') plus a worked example ('we sampled 400 culled docs and found 2 relevant'). It also names the alternative tool and the condition that selects it (overall recall % from the same sample), which is exactly the when/when-not routing an agent needs.

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

All eDiscovery Decoder News/Calc 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.

Resources

Need Help?