Skip to main content
Glama
Sign In
Uoink

Uoink

by ryanbiddy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Find research evidence

research_evidence

Find cue-aligned evidence in a research run's selected ready sources, returning revision-bound excerpts, timestamp links, and ASR doubt spans while saving membership and call history.

Instructions

Find cue-aligned evidence only in a research run's selected ready sources. Returns untrusted excerpts inside the library's escaped JSON fence, revision-bound ids, timestamp links and ASR doubt spans. Quotes are the unescaped words, not the escape sequences. Saves excerpt membership and call history locally. Windows are at most 120 seconds and 200 cues. Counter stance only expands the search query. Each call consumes one of the run's 10 evidence calls; no network or library writes.

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>",
      "query": "<query>"
    },
    "name": "research_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum rows to return in this response; does not change stored data.
queryYesNonempty search text to match against saved content.
run_idYesResearch run_id returned by research_start.
stance_hintNoOptional: support or counter. Use counter on at least one call for contested points.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.14.0

TDQS

A4/5.0
Behavior5/5

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

Goes well past the annotations, which only mark this as a non-read-only, non-idempotent, closed-world call. The description explains why: excerpt membership and call history are persisted locally, while no network or library writes occur, and it discloses untrusted-excerpt fencing, revision-bound ids, ASR doubt spans, the 120s/200-cue window cap, and a 10-call budget.

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?

Purpose is stated up front and nearly every sentence carries non-obvious information, including the note that quotes are unescaped words rather than escape sequences. The prose is telegraphic and lacks structure, but there is little waste.

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?

With no output schema, the description shoulders the burden of describing returns and does so (excerpts, ids, timestamp links, ASR doubt spans). Missing are pagination/limit interaction and how budget exhaustion surfaces, but the essential call-shaping information is present.

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 baseline is 3, but the description adds real meaning beyond the schema by clarifying that 'counter' stance only expands the query rather than filtering to contrary evidence. It adds nothing about limit or run_id, which the schema already covers well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find cue-aligned evidence') and constrains scope to 'a research run's selected ready sources', which implicitly separates it from search_library, search_clips and get_evidence_card. It does not name a sibling outright, so differentiation is inferred rather than explicit.

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?

Usage context is implied by the requirement of a run_id and the note that each call consumes one of the run's 10 evidence calls, which tells the agent to budget calls. However, there is no explicit when-to-use versus alternatives (e.g. research_capture, get_evidence_card) 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.

Deploy Server

Other Tools