Skip to main content
Glama

search_feedback

Search analyzed customer calls for sentences containing your keywords and return matching quotes with call ID and time. Filter by speaker, date range, and result limit.

Instructions

Search what was said in the analyzed calls. All words must appear in the same sentence; case and accents are ignored. speaker: "customer" (default), "agent", or null for both. Returns the matching sentences with their call id and time. Read-only.

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": {
      "query": "<query>"
    },
    "name": "search_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes
sinceNo
untilNo
speakerNocustomer

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

With zero annotations, the description carries the full burden and does notable work: it declares the tool read-only, explains the matching semantics (all words must co-occur in one sentence, case and accents ignored), and states the return shape (matching sentences with call id and time). Gaps remain around the limit/pagination behavior and any scoping or permission constraints on analyzed calls.

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?

Front-loaded with purpose, then matching rules, then parameter notes, then return shape and safety. Compact and low-waste, though the sentence fragment starting with 'speaker:' breaks the prose structure and would read better as a clause.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description does cover the return value, which is a plus. However, for a five-parameter tool with 0% schema coverage and no annotations, the undocumented `since`/`until`/`limit` parameters leave an agent guessing about date formats and result caps.

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 0%, so the description must compensate. It does well for the two most important parameters: the required `query` (all words same sentence, case/accent insensitive) and `speaker` (allowed values customer/agent/null, default customer — information the schema lacks since there is no enum). It says nothing about `limit`, `since`, or `until`, leaving three of five parameters, including date formats, undocumented.

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: search what was said in analyzed calls, returning matching sentences. This is clearly distinguishable from insight-oriented siblings like get_call_insights or analyze_call, though the description never names an alternative to sharpen the contrast.

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 is implied by the purpose (find sentences containing given words in call transcripts), and the same-sentence requirement hints at the query model. There is no explicit when-to-use or when-not guidance, and no pointer to the sibling tools for broader analysis needs.

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