Skip to main content
Glama

find_evidence

Fact-check or substantiate a claim against the corpus. Given a textual claim, retrieves and CLASSIFIES evidence into supporting / contradicting / neutral groups. Uses HyDE (hypothetical document expansion) — server generates plausible supporting/contradicting text, embeds, retrieves, then ranks by relation to original claim. Returns chunks with selfContained flag (safe-to-cite indicator). Use for fact-verification, controversy mapping, 'is this claim known?' queries. Modes: 'fast' (~3s, symmetric-by-construction grouping) / 'deep' (~10s, independent NLI classification). IMPORTANT: in 'fast' mode the supporting/contradicting counts are approximately balanced BY CONSTRUCTION and do NOT reflect actual literature distribution. Use 'deep' when measuring controversy balance, literature distribution, or any claim of the form 'the field is split N:M on this'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo'fast' (~3s): retrieval uses symmetric HyDE pools — top-20 chunks against the supporting-hypothetical plus top-20 against the contradicting-hypothetical, then each chunk is assigned to the bucket whose HyDE-vector it scored higher against. Because the retrieval pool is symmetric and the classification mirrors the retrieval direction, supporting/contradicting counts come out approximately balanced regardless of the actual distribution of evidence in the corpus (a topic that is 90% supported in the literature will still show a ~1:1 split here). Use fast mode for 'is there evidence on either side?', not for 'how is the field actually split?'. May also misclassify chunks that mention the topic but logically point the other way (e.g. a paper explaining 'BN is bad in transformers' may land in the contradicting bucket for an 'LN > BN' claim). 'deep' (~10s): adds an independent per-chunk LLM NLI classification on top of the union pool, so counts reflect actual semantic distribution and can be arbitrarily asymmetric. Use 'deep' whenever classification accuracy or distribution shape matters — including controversy mapping and any analysis that interprets the supporting/contradicting ratio as a signal about the field.fast
claimYesStatement to fact-check or substantiate
limitNoMax results PER group (supporting/contradicting/neutral)
detailNostandard
run_idNoOptional. The active methodist run_id (as returned by the methodist diagnose / get_current_dose door). Pass it whenever you call this tool while working inside a run, so the call is attributed to that run for the §8 usage crosscheck — attribution is run-anchored, so it stays correct even if your access token refreshes mid-run. Must be YOUR run: a run_id owned by a different principal, or a non-existent run_id, is rejected.
categoriesNo
selfContainedOnlyNoIf true, only return chunks marked as understandable without prior context (safer to cite)

TDQS

A4.9/5.0
Behavior5/5

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

The description fully discloses the HyDE technique, the symmetric-by-construction grouping in 'fast' mode, the resulting artificial balance of supporting/contradicting counts, and potential misclassification. With no annotations provided, the description carries the full burden and does so comprehensively without contradiction.

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?

The description is well-structured with the purpose first, then mode details, then parameter notes. It is comprehensive but slightly long; however, every sentence adds necessary value, so only minor conciseness improvement is possible.

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?

Given 7 parameters and no output schema, the description covers all essential behavioral aspects: mode caveats, limit per group, run_id attribution, and selfContained flag. The complexity of the HyDE-based classification is fully explained, making the tool complete for agent understanding.

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?

Although schema coverage is high (71%), the description adds significant contextual meaning beyond the schema, especially for 'mode' (explaining the retrieval and classification process in both modes), 'run_id' (its attribution purpose and requirement), and 'selfContainedOnly' (safety context).

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 with a specific verb-resource pair ('Fact-check or substantiate a claim against the corpus') and clearly distinguishes the tool from siblings like 'find_related' or 'search' by focusing on evidence classification into supporting/contradicting/neutral groups.

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 use cases are given ('fact-verification, controversy mapping, 'is this claim known?' queries') and a detailed warning explains when 'fast' vs 'deep' mode should be used, including a critical caveat about balanced counts in 'fast' mode that prevents misinterpretation.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

Most tools have clear distinct purposes, but some overlap exists between explore_topic and methodist_explore_topic, and between find_related and find_related_claims. Descriptions generally differentiate them well.

Naming Consistency4/5

Tool names follow a consistent verb_noun pattern with methodist_ prefix for research workflow tools, though 'paginate' and 'methodist' (without underscore) are minor deviations.

Tool Count2/5

35 tools is too many for a single server's scope, exceeding the 25+ threshold. The server combines two major workflows (literature search and research process guidance), which would be better split.

Completeness4/5

The tool set covers a wide range of operations: multiple search modes, document submission and versioning, topic exploration, evidence checking, methodology search, and research guidance. Minor gaps include lack of document deletion or metadata update without new version.