Skip to main content
Glama
Sign In
Uoink

Uoink

by ryanbiddy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Publish research report

research_publish
Idempotent

Verify research claims against stored excerpts and current transcript revisions, then write Markdown, escaped HTML, and verification ledger reports inside the research run.

Instructions

Verify research claims against this run's stored excerpts and current transcript revisions, then write a local Markdown report, escaped HTML report and verification ledger. Submit quotes as unescaped words, not escape sequences. Renders only matched stored text; drops unbound or ambiguous quotes and judge=no claims. Flags ASR doubt, unconfirmed speakers, overstatement, low overlap and one-sided search. Enforces quote/source caps. Reuses a saved result only when the payload, source revisions, run evidence and output paths are unchanged. No network; writes only inside the research run.

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": {
      "run_id": "<run_id>",
      "title": "<title>",
      "summary_md": "<summary_md>",
      "claims": "<claims>"
    },
    "name": "research_publish"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYesDisplay title for the saved content; omit to use the handler's derived/default title.
claimsYesAgent-extracted objects with claim_text, optional check_worthiness from 0 to 1 and optional context object. Invalid entries are skipped and reported in errors.
run_idYesResearch run_id returned by research_start.
summary_mdYesReport summary Markdown, at most 1500 characters, with no URLs.
disagreementsNoOptional, up to 10 contested topics, each naming 2-6 claim_ids that disagree.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.14.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare the safety profile (readOnly=false, destructive=false, idempotent=true, openWorld=false); the description adds substantial behavior beyond that — quote binding rules, dropping of unbound/ambiguous/judge=no claims, quality flags raised, cap enforcement, cache-reuse conditions, and the 'no network, writes only inside the research run' boundary. The only shortfall is that the return payload (paths vs. ledger contents vs. drop report) is never characterized.

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?

Six tightly packed sentences, front-loaded with the purpose before behavioral detail, and no filler. Density is high but each sentence carries a distinct rule (binding, drop behavior, flags, caps, caching, sandbox). It could be broken into a short purpose line plus a behavioral block for faster scanning.

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 5-parameter, non-idempotent-looking write tool with no output schema, the description covers inputs' rules, drop conditions, flags, and filesystem/network scope well. The remaining gap is that an agent cannot tell what the call returns (paths, ledger object, or error list) given the absence of an output schema.

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 baseline is 3; the description earns above that by adding rules the schema cannot express: quotes must be submitted as unescaped words rather than escape sequences, and only matched stored text renders while unbound or ambiguous quotes are silently dropped. It still does not interpret required fields such as run_id or the claims array structure beyond what the schema already states.

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 compound verb chain and three named artifacts: 'verify research claims against this run's stored excerpts... then write a local Markdown report, escaped HTML report and verification ledger.' That output signature (reports + ledger, scoped to a run) makes it distinguishable from siblings like verify_claim, extract_claims and research_evidence without opening any schema.

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?

Usage context is clear: it operates on 'this run's' excerpts and transcript revisions, and it reuses a saved result only when payload, revisions, evidence and output paths are unchanged. What is missing is any explicit exclusion or named alternative (e.g., when to use verify_claim or research_evidence instead of publishing).

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