TalaLevel

Search calls

search_calls

Read-onlyIdempotent

Find calls, newest first: one lead's, a day's or a week's, by who made them (this person, a teammate, or the AI caller), by how far they got (reached a human, voicemail, no answer …), by length, or by words in the lead's name or the call's summary. Each row has the call id, lead, when, direction, length, outcome and a short summary; read one with get_call. For what was said across many calls, search_what_was_said is better.

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": "search_calls"
  }
}

Input Schema

Name	Required	Description
`by`	No	me, ai (the AI caller), or a teammate's person id (list_team).
`from`	No	Calls on or after this day.
`limit`	No	How many to return, at most 50 (more is cut to 50).
`query`	No	Words in the lead's name or the call's summary.
`cursor`	No	The cursor a previous page of this tool gave, to read the next page. Leave it out for the first.
`lead_id`	No	Only this lead's calls.
`reached`	No	How far the call got, as the answers spell it: human, voicemail, no_answer, gatekeeper, wrong_number …
`through`	No	Calls on or before this day.
`direction`	No
`min_seconds`	No	Only calls at least this long.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds real value beyond them: results are ordered newest first and each row carries id, lead, time, direction, length, outcome and a short summary. It does not mention auth requirements or rate limits, but for a read-only search those are minor.

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 the verb and the newest-first ordering, then the filter axes, then the sibling routing — a logical progression with no filler. The first sentence is long and clause-heavy, which slightly slows scanning, but every clause conveys a distinct filter dimension.

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 10 optional parameters and no output schema, the description compensates by describing the returned row fields and the newest-first ordering, and by pointing to get_call for full records. Nothing an agent needs in order to call this correctly is missing.

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 description coverage is already 90%, so the baseline is 3; the description goes further by mapping parameters onto natural language intent ("one lead's, a day's or a week's, by who made them … by how far they got"), clarifying that `by` accepts this person, a teammate, or the AI caller, and that `reached` uses answer wording. It does not restate the limit cap or cursor usage, which live in the schema.

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?

States a specific verb+resource ("Find calls") and immediately enumerates the filter axes: by lead, day/week, who made them, how far they got, length, or words in the name/summary. It also names the sibling for reading a single call (get_call), so an agent can distinguish it from retrieval tools without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing: "read one with get_call" and "For what was said across many calls, search_what_was_said is better." These are clear when-to-use-this vs when-to-use-alternative statements, plus an implicit exclusion (this tool is not a transcript search).

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

All TalaLevel tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?