Skip to main content
Glama
Sign In

Traceo

by io.github.muhamad-0
OverviewDiscussionsAdmin

Get video frames

get_frames
Read-onlyIdempotent

Stills from the recording video, captured after each click, error and failed request plus an even spread. Pass at_s to see the screen at a moment (e.g. the time of an error from get_timeline), or from_s/to_s for a range. Returns up to 6 images.

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": {
      "recording": "<recording>"
    },
    "name": "get_frames"
  }
}

Input Schema

NameRequiredDescriptionDefault
at_sNoSeconds from the start: returns the frames nearest this moment.
to_sNoEnd of a range in seconds.
limitNoHow many frames (default 3).
from_sNoStart of a range in seconds.
recordingYesTraceo share link (e.g. https://www.traceo.dev/abc123...) or recording id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare this a safe, idempotent read, so the bar is lower, and the description still adds real behavior: which moments get captured, the even-spread sampling, and a hard cap of 6 images. It does not say what happens when a recording has no video or no click events, which is the remaining gap.

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, no filler: what the frames are and how they are chosen, then how to query by moment or range, then the return cap. The most decision-relevant information is front-loaded.

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 correctly carries the return shape (up to 6 images) and the sampling behavior an agent needs to interpret results. Minor omissions around empty/failed cases for recordings without video keep it from a 5.

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 baseline is 3, but the description goes further by explaining the mutual role of at_s versus from_s/to_s — a relationship the schema documents independently but does not connect. It also mentions the up-to-6 image ceiling that bounds limit, though it omits the stated default of 3.

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?

The description names the resource precisely (still frames from the recording video) and discloses the capture policy — after each click, error and failed request, plus an even spread. That is far more specific than a bare 'get frames'. It stops short of explicitly contrasting with a sibling such as get_thumbnail, so it does not fully earn a 5.

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

Usage Guidelines4/5

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

It tells the agent exactly how to drive the tool for two distinct intents: at_s for a single moment and from_s/to_s for a range. It even cross-references get_timeline as the source of the error timestamp worth sampling. It gives no explicit when-not-to-use case (e.g. preferring get_thumbnail for a single preview), so it falls short of 5.

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

All Traceo 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