Skip to main content
Glama

FutureSmart AI Demos

by com.aidemos

get_evidence

Query the evidence graph: observation cells (tool × test-scenario × criterion) → verdict, score, the researcher's note, and the REAL artifacts (input/output screenshots) that prove it. The ground truth behind every ranking — filter any combination of tool(s), scenario (slug, group tag, or name), criterion, verdict, or evidence state. evidence_state: "verified" = artifact-backed, "observed" = noted without artifact, "scored-only" = number only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toolNoTool slug or name, e.g. "landing-ai".
limitNoMax cells (default 50).
toolsNoSeveral tools at once.
rankingNoRanking page slug — scope cells to the evidence run that published ranking is bound to (exactly what the page renders).
verdictNo
evidenceNo
scenarioNoScenario slug, cross-run group tag (e.g. "scanned-research-paper"), or name fragment.
criterionNoCriterion slug or name, e.g. "table extraction".

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are provided, so the description carries full burden. It accurately describes the output (verdict, score, note, artifacts) and explains the three evidence states. It does not explicitly state read-only behavior or potential side effects, but the nature of a query tool and the output description strongly imply no mutations. The description is transparent about what the tool returns and its filtering capabilities.

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 is a single, well-structured paragraph that front-loads the primary action ('Query the evidence graph') and then details the output and filter options. Every sentence is informative with no wasted words. It is concise yet comprehensive.

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 tool with 8 parameters, no output schema, and no annotations, the description provides a good level of completeness: it describes the output (verdict, score, note, artifacts), explains evidence states, and lists all filterable fields. It lacks details on output format or pagination beyond the limit parameter, but is sufficient for correct invocation.

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?

The input schema covers 75% of parameters with descriptions. The tool description adds extra meaning by explaining the evidence_state values ('verified', 'observed', 'scored-only') and reinforcing the filterable fields. This goes beyond the schema's enum definitions, adding semantic clarity for the agent.

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 clearly states the tool queries the evidence graph and returns observation cells with verdict, score, note, and artifacts. It lists the filterable dimensions (tool, scenario, criterion, verdict, evidence state) and explains the meaning of evidence_state values, making the purpose very specific and distinct from sibling tools like get_ranking or compare_tools.

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?

The description explains what the tool does and its filters, but does not explicitly state when to use it versus alternatives (e.g., get_ranking for summary, tools_in_ranking for listing). It implies it's for detailed evidence behind rankings, but lacks explicit when-to-use or when-not-to-use guidance.

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

All FutureSmart AI Demos 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

A3.8/5.0
Disambiguation5/5

Every tool targets a distinct entity or action: list tools enumerate different content types, get tools retrieve specific entities, search finds across the catalogue, compare_tools does head-to-head comparison, and the two cross-reference tools (rankings_for_tool and tools_in_ranking) are inverse operations. No two tools have overlapping purposes.

Naming Consistency4/5

Most tools follow a consistent verb_noun pattern (list_*, get_*, compare_tools, search), but 'rankings_for_tool' and 'tools_in_ranking' deviate with a noun_prep_noun pattern. These two are internally consistent with each other and remain readable, so the overall convention is only slightly disrupted.

Tool Count4/5

16 tools is slightly above the ideal 3-15 range but still well-scoped for a catalogue covering seven entity types, search, comparison, and cross-references. Each tool has a distinct role and none are redundant, so the count feels justified rather than bloated.

Completeness4/5

The tool surface covers all major content types with list and get (except categories and toolkits, which only have list endpoints), plus search, comparison, and inverse cross-references. Minor gaps like missing get_toolkit or get_category are workaround-able since list_toolkits and list_categories expose sufficient metadata.

Resources