Skip to main content
Glama

Metis — Weigh Evidence

weigh_evidence

Report the full spread of quantified evidence in your corpus—individual estimates with provenance, qualifiers, gaps, and dates—instead of a single answer.

Instructions

What does the evidence in the corpus actually say about a quantity?

Fact-checking a number is not the same as checking a citation. A figure can be
correctly cited and still be one of many the literature reports — this corpus
can hold specificity estimates for one test family ranging from 72% to 99.7%, and a
single confident answer hides that entirely.

So this reports the SPREAD, never one value: every quantified statement found,
with its document and page, the qualifiers attached to it (sample size,
confidence interval, reference standard, population, setting, threshold), what
is MISSING from each, sentences nearby that complicate the figure, and how old
the evidence is. Deterministic — lexical retrieval and regex, no model, so it
can miss an oddly-phrased figure but cannot invent one.

Use it before answering any "what is the X of Y" question. Then use
`check_for_newer_evidence` to find out whether the corpus is current.

Args:
    question: The question as asked, e.g. "specificity of the RDT in community screening".
    layers: Comma-separated layer slugs to restrict to; omit to search all.
    show: How many individual findings to list (default 14).

Returns:
    Per-metric spread, the individual estimates with provenance and
    qualifiers, the qualifier gaps, and the evidence date range.

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": {
      "question": "<question>"
    },
    "name": "weigh_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
showNo
layersNo
questionYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.5

TDQS

A4.7/5.0
Behavior5/5

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

No annotations exist, and the description carries the full load well: it discloses the method (deterministic lexical retrieval plus regex, no model), the resulting failure mode ('can miss an oddly-phrased figure but cannot invent one'), that it never collapses to one value, and that it surfaces qualifier gaps and evidence age. That is exactly the behavioral context an agent needs before trusting the output.

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?

Front-loaded with the core question, then rationale, then the usage directive, then Args/Returns — a sensible order. The 72%–99.7% spread anecdote is long but earns its place by motivating why the tool reports a range rather than a value; the Returns block is partly redundant given the output schema exists.

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

Completeness5/5

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

For a 3-parameter read tool with an output schema, the description covers purpose, trigger, follow-up tool, retrieval mechanism, known limitation, and per-parameter meaning. Nothing an agent needs in order to call it correctly or interpret its limits is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate — and it does, documenting all three parameters: `question` with a worked example, `layers` as comma-separated slugs where omission means all layers, and `show` as the count of listed findings (default 14). Every parameter gets meaning beyond its bare name and type.

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?

States a specific verb and resource — reports the SPREAD of every quantified statement about a quantity in the corpus, with document, page, qualifiers, gaps and age. It also explicitly contrasts itself with citation verification ('fact-checking a number is not the same as checking a citation') and with `check_for_newer_evidence`, so an agent can separate it from `verify_claim`/`verify_text_citations` without opening a schema.

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

Usage Guidelines4/5

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

Gives a concrete trigger — 'use it before answering any "what is the X of Y" question' — and names the sibling to run next (`check_for_newer_evidence`). It stops short of stating when NOT to use it (e.g., non-quantified questions, or when a single verified value is wanted via `verify_claim`), so it is clear context without full exclusion rules.

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