Skip to main content
Glama

Zetesis Scientific Due Diligence

by io.github.reutavidan

zetesis_evidence

Read-only

Step 2 of a Zetesis evaluation. Runs the search queries against public evidence sources (Europe PMC, ClinicalTrials.gov, openFDA, and optionally NIH RePORTER and SEC EDGAR) and returns a deduplicated bundle where every source carries a hard public id, followed by the Zetesis grading rubric so you can grade the dimensions yourself.

With as_of set, retrieval is fenced to sources published, registered, or filed on or
before 31 December of that year, and two fields that leak later outcomes are
suppressed: a trial's present-day status, and FDA labels effective after the cutoff.
That makes it possible to judge a claim on what was actually knowable at the time.

Runs no model, costs nothing, and returns immediately. Use zetesis_scope first to
choose the queries. Together the two make up the preferred route into Zetesis.

Args:
    queries: 3 to 6 short keyword phrases. Query 1 should be the bare name of the
        thing claimed about (a drug, compound code, model, or gene); query 2 that
        name plus at most two outcome words. Longer phrases retrieve commentary
        rather than the primary report.
        If the claim names no agent at all (a behaviour, diet, procedure, exposure
        or policy), anchor on the field's own technical term instead of the lay one
        ("time restricted eating", not "intermittent fasting"), pair it with the
        outcome as the field measures it, and allow one design word such as
        crossover or randomized in one later query. Without an entity name that
        design word is the only thing separating a trial report from a review of
        trial reports.
    as_of: optional cutoff year, as used in zetesis_scope.
    include_capital: also retrieve funding and public-filing signal.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
as_ofNo
queriesYes
include_capitalNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare read-only/open-world/destructive false; the description adds substantial behavior: deduplication, hard public ids, inclusion of the grading rubric, as_of date fencing, suppression of later-leaking trial status and FDA labels, and 'Runs no model, costs nothing, and returns immediately'. No contradiction with the annotations exists.

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?

The description front-loads purpose and behavioral facts before diving into Args, and the structure cleanly separates narrative guidance from parameter guidance. The longer query guidance earns its length because it teaches the agent how to avoid commentary instead of primary reports.

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?

With an output schema available, the description does not need to enumerate every return field. It covers sources, id guarantee, rubric inclusion, as_of behavior, cost/performance expectations, and pipeline integration with zetesis_scope, giving an agent enough context to invoke the tool correctly.

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%, but the Args section fully compensates. queries gets detailed construction rules, count, ordering, and a no-entity strategy with concrete examples; as_of is tied to cutoff semantics and zetesis_scope; include_capital is explained as funding/public-filing signal.

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 opens by identifying the tool as 'Step 2 of a Zetesis evaluation' and states exactly what it does: 'Runs the search queries against public evidence sources' and returns a deduplicated bundle with hard public ids. It names the concrete sources and sets up the relationship to zetesis_scope, making its role unmistakable.

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?

It explicitly instructs the agent to 'Use zetesis_scope first to choose the queries' and calls the pair 'the preferred route into Zetesis', which is strong sequencing guidance. However, it does not contrast the tool with evaluate_claim or verify_attestation, so exclusion/alternative guidance is incomplete.

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

All Zetesis Scientific Due Diligence toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0
Disambiguation5/5

Each tool has a distinct role: scoping, evidence retrieval, hosted evaluation, and attestation verification. The descriptions explicitly route the agent between them, so overlap is minimal.

Naming Consistency3/5

Two tools follow verb_noun naming (evaluate_claim, verify_attestation) while two follow zetesis_ + noun naming (zetesis_scope, zetesis_evidence). The set is readable and consistently snake_case, but the pattern is not predictable across all tools.

Tool Count5/5

Four tools is well-scoped for the server's purpose: scope, evidence, evaluate, and verify. Each tool earns its place and none is redundant.

Completeness5/5

The tool set covers the full due-diligence workflow from scoping and evidence retrieval to optional hosted evaluation and attestation verification. The token-gated evaluate tool is backed by a complete no-token route, so there are no critical dead ends.

Resources