Skip to main content
Glama
wdi-decision-intelligence

wdi-decision-intelligence

grade_evidence

Read-only

Classify each claim behind a decision as KNOWN, ASSUMED, UNKNOWN, or SYNTHETIC and receive a recommended next step for each.

Instructions

Tag each claim behind a decision as KNOWN, ASSUMED, UNKNOWN or SYNTHETIC and suggest the next step for each.

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": {
      "claims": "<claims>"
    },
    "name": "grade_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
claimsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered; the description adds that output includes a per-claim next-step suggestion, which is useful. However it never explains the criteria used to assign a tier (what makes a claim KNOWN vs ASSUMED), nor whether pre-supplied tiers are honored or overwritten — the key behavioral question for a grading tool.

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

Conciseness5/5

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

One sentence, front-loaded with the action and resource, with the output behavior appended. No filler and nothing redundant.

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?

With one required parameter, no output schema, and read-only annotations, the description covers purpose, taxonomy, and the shape of the result (tiers plus next steps). The remaining gap is the grading criteria and how the polymorphic claim input is handled, which matters more here than for a simple lookup tool.

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 has to carry meaning, and it does clarify that the array elements are 'claims behind a decision' and that the four tier labels are the vocabulary. It does not address the schema's polymorphism (elements may be bare strings or objects) or the meaning of the optional source field and pre-set tier.

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 ('Tag') and resource ('each claim behind a decision'), then enumerates the four tier labels and the secondary action ('suggest the next step'), so an agent knows exactly what the tool produces. It does not name or contrast any sibling (calculate_runway, compare_options, six_dimension_checklist), but the purpose is distinct enough to separate them.

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 only implied by the phrase 'behind a decision' — an agent can infer this is for auditing evidence supporting a choice, but there is no explicit when-to-use, when-not-to-use, or prerequisite (e.g., whether raw claims must be gathered first). No alternative is named.

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