Skip to main content
Glama

diagnose_perception

Watches robot cameras, depth sensors, and point clouds to report dead or stale streams, low rates, bad or frozen images, invalid depth, empty clouds, and missing camera_info.

Instructions

Watch the cameras, depth sensors and point clouds on a running robot and report a dead or stale stream, low rate, dark, blown-out or frozen images, mostly invalid depth, empty clouds and missing camera_info. Read-only. Uses percept_doctor.

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": "diagnose_perception"
  }
}

Input Schema

NameRequiredDescriptionDefault
nsNo
secondsNo
domain_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations present, the description must carry the behavioral burden. It does disclose 'Read-only' and reveals the underlying mechanism ('Uses percept_doctor'), plus what it inspects and what symptoms it reports. It does not say whether a live ROS graph/DDS connection is required, what the report looks like, or how failures are surfaced — meaningful gaps for a zero-annotation tool.

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?

The description is front-loaded with the action and scope, then closes with two short high-value facts ('Read-only', 'Uses percept_doctor'). The dense failure-mode list is long but each item is substantive, so little is wasted.

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?

The symptom list partially substitutes for a missing output schema by telling the agent what findings to expect, and 'Read-only' covers the safety profile. But with three undocumented parameters, no annotations, and no output schema, the definition leaves the agent guessing about scope selection (namespace, domain) and observation duration.

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

Parameters2/5

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

Schema description coverage is 0% for all three parameters (ns, seconds, domain_id), so the description must compensate and does not — none of the three are mentioned. In particular 'seconds' (the observation window, default 8) and 'domain_id' (ROS domain selection) are non-obvious and left entirely undocumented.

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?

The description uses a concrete verb ('Watch...and report') against a specific resource set — cameras, depth sensors and point clouds on a running robot — and enumerates the exact failure classes it detects (dead/stale stream, low rate, dark, blown-out, frozen images, invalid depth, empty clouds, missing camera_info). That specificity makes it trivially separable from the diagnose_arm/diagnose_nav2/diagnose_slam siblings, which cover different subsystems.

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 context is implied rather than stated: 'on a running robot' tells the agent a live system is required, and the failure-mode list implies when the tool is useful. However, it never says when to prefer this over other diagnostics or when not to call it (e.g. robot not running, non-perception issues), and names no alternative.

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