Skip to main content
Glama

Search the KOL evidence archive

evidence_search
Read-onlyIdempotent

Archived posts of measured KOLs with the exact post time, including posts later deleted from X. Give a handle, words (or a $ticker), or both. Returns at most 10 records with links and record hashes.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "evidence_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
wordsNoWords or a $ticker to find in the posts, e.g. $PEPE. Optional when handle is given
handleNoX handle of a measured KOL without @, e.g. cobie. Optional when words is given
deleted_onlyNotrue returns only posts that were later deleted from X

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / deleted_only / description
      Added value: +"true returns only posts that were later deleted from X"
    • addedInput schema / properties / handle / description
      Added value: +"X handle of a measured KOL without @, e.g. cobie. Optional when words is given"
    • addedInput schema / properties / words / description
      Added value: +"Words or a $ticker to find in the posts, e.g. $PEPE. Optional when handle is given"
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive behavior, so the bar is lower. The description still adds meaningful context beyond them: coverage extends to posts later deleted from X, results are capped at 10, and records carry links and hashes. It does not explain whether the cap means truncation (and how to page beyond it), which would have pushed this higher.

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?

Three short sentences: what the archive contains, how to query it, and what comes back. Front-loaded with the distinguishing facts (deleted posts, result cap) and no redundant wording.

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 carries the return-shape burden and does so at a high level (max 10 records, links, record hashes). The main residual gap is pagination or what happens when more than 10 matches exist, which matters for a search tool an agent may need to iterate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all three parameters including the $ticker example and the deleted_only semantics are already documented structurally. The description restates the handle/words/both options without adding syntax, formats, or edge-case behavior, so the schema does the heavy lifting and baseline 3 applies.

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?

"Archived posts of measured KOLs" names a specific resource and scope, and the added detail about exact post time, deleted posts, and links/hashes makes the retrieval target concrete. It stops short of explicitly contrasting itself with kol_lookup or organic_interest, so an agent must infer that this is the post-level search rather than a profile or aggregate lookup.

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?

"Give a handle, words (or a $ticker), or both" tells the agent how to compose a query, which is genuine invocation guidance. It says nothing about when to prefer this tool over the sibling lookup/aggregate tools, so usage context remains implied rather than stated.

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.