Skip to main content
Glama

Metis — Weigh Evidence

weigh_evidence

Report the full spread of quantified evidence for a research question—including each estimate’s source, page, qualifiers, and missing context—instead of returning one value.

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
holds specificity estimates for HAT serology 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 CATT in passive 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.

Input Schema

NameRequiredDescriptionDefault
showNo
layersNo
questionYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.5

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the retrieval mechanism (lexical + regex, no model), the consequence ('can miss an oddly-phrased figure but cannot invent one'), the deliberate refusal to aggregate to one value, and the qualifier/gap/date-range content of the response. This is exactly the behavioral context an agent needs for a research-evidence tool.

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 and the spread-not-single-value rationale before mechanics. The 72%-99.7% specificity example is illustrative and slightly indulgent, but it does real work explaining why spread reporting matters; the Args/Returns blocks are tight.

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?

Covers purpose, mechanism, output shape, and next-step tool, plus documented parameters. An output schema exists, so the Returns section is mild redundancy rather than a gap. Nothing needed to invoke it correctly is missing.

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

Parameters4/5

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

Schema description coverage is 0%, but the Args block compensates: question is given an example phrasing, layers is explained as comma-separated slugs with an explicit 'omit to search all' default semantic, and show is defined as the number of findings with default 14. All three parameters gain meaning beyond the bare types in the schema.

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: it reports the SPREAD of quantified evidence about a quantity, not a single value. The opening contrast with fact-checking a citation sharpens what the tool is and is not, distinguishing it from siblings like verify_claim and verify_text_citations.

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?

Explicit instruction: 'Use it before answering any "what is the X of Y" question,' followed by the sequencing rule to call check_for_newer_evidence afterwards. It also states when not to expect the tool's output to be a single answer, pre-empting misuse.

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