Skip to main content
Glama
Sign In

TalaLevel

by com.talalevel.app
OverviewDiscussionsAdmin

Search what was said

search_what_was_said
Read-onlyIdempotent

Find merchants by what was said or written: one search over texts, call transcripts and summaries, emails, notes, what leads told us, and file reviews, first for the words (a quoted phrase, a minus to drop a word) and then for rows that mean the same thing ("asked about rates" also finds "what's the APR"). Each hit says which and where it is, with the line itself. Use it for "who mentioned a lease", "which merchants asked about rates", "did anyone say they'd call back Monday"; use search_leads for a name, number or email.

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_what_was_said"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromNoOn or after this day.
kindsNoOnly these kinds: text, transcript, summary, email, note, memory, review.
limitNoHow many to return, at most 50 (more is cut to 50).
queryYesWhat was said, in words or in meaning.
lead_idNoOnly this lead's.
throughNoOn or before this day.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent and non-destructive, so safety is covered. The description adds behavior the annotations cannot: a two-stage search (literal words first, then semantic matches such as 'asked about rates' matching 'what's the APR') and that each hit reports which source and the matching line. It omits mention of the hard 50 cap on limit, which is a minor gap.

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 purpose, then sources, then query behavior, then examples and the sibling exclusion — a sensible order with no filler. The middle sentence is dense with long clause chains, which costs a little readability but not correctness.

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?

There is no output schema, so the description usefully says what a hit contains (which source, where, and the line itself). Combined with full schema parameter coverage, an agent has enough to call this correctly; only the effective result cap is left implicit.

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 already 100%, so baseline is 3; the description earns more by explaining query syntax and semantics — quoted phrases and a minus to drop a word, plus meaning-based matching. It does not elaborate on from/through/kinds/lead_id, but those are adequately described 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?

Specific verb and resource: 'Find merchants by what was said or written', and it enumerates the sources searched (texts, transcripts, summaries, emails, notes, lead statements, file reviews). It also explicitly contrasts with search_leads, so the agent can separate this tool from a sibling 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?

Gives concrete when-to-use examples ('who mentioned a lease', 'did anyone say they'd call back Monday') and an explicit exclusion with the alternative named: 'use search_leads for a name, number or email'. The routing rule is unambiguous.

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

All TalaLevel toolsInspect
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