Skip to main content
Glama
Sign In
Zearch MCP

Zearch MCP

Official
by zearchcomputer
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Verify text against sources

verify
Read-onlyIdempotent

Check text against its cited sources paragraph by paragraph to confirm support and attribution, returning pass/fail results for gating model output before people see it.

Instructions

Check text against the sources it cites, paragraph by paragraph, with Jev (the same check Zearch runs on its own answers). Cite sources inline as [1], [2]… in the order you list them. Use it to gate output from your own model before a person sees it.

Limits: text up to 8,000 characters; 1 to 8 sources of up to 20,000 characters each. Costs 1 credit, charged only when the check completes. Returns pass/fail per paragraph with support and attribution probabilities.

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": {
      "text": "<text>",
      "sources": "<sources>"
    },
    "name": "verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesMarkdown to check. Every paragraph should cite at least one source as [n].
sourcesYesSources in citation order: the first is [1].
questionNoThe question the text answers, if any. Improves the check.

Output Schema

NameRequiredDescriptionDefault
modelNo
objectNo
passedYesTrue when every paragraph met the support threshold.
thresholdNo
paragraphsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only cover the read-only/idempotent safety profile, and the description adds genuinely new operational facts: a 1-credit cost that is charged only on completion, hard limits of 8,000 characters of text and 1-8 sources of 20,000 characters each. Those billing and input-size constraints are the kind of detail an agent cannot infer from structured fields and must know before calling.

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?

Two short paragraphs: purpose and usage first, then a clearly labeled "Limits:" block with cost and return shape. The citation-format rule sits immediately after the purpose where it is needed, and no sentence is padding.

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 annotations, a full output schema, and complete schema coverage already in place, the description supplies the remaining decision-critical context: what it is for, input formatting rules, size limits, and cost timing. An agent can decide to call it and construct valid input without opening anything else.

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 coverage is 100%, so the per-field baseline is 3, but the description adds cross-parameter meaning the schema does not spell out: citations must appear inline as [1], [2]… in the same order the sources are listed, making the positional coupling between text and sources explicit. The optional question parameter is left to the schema, which is reasonable.

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?

"Check text against the sources it cites, paragraph by paragraph" names a specific verb (check), resource (text vs. cited sources), and granularity (per paragraph). The parenthetical about Jev/Zearch clarifies it is a source-verification check rather than a research or retrieval tool, which cleanly separates it from siblings like research or list_runs.

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?

"Use it to gate output from your own model before a person sees it" gives an explicit triggering scenario, and the citation-format instruction tells the agent how input must be prepared. It does not name when not to use it or point to an alternative sibling, so it stops just short of a 5.

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