Paw Pulse

Create monitor

create_monitor

Create a new anonymous Paw Pulse monitor. Returns ingest_token and manage_token exactly once — store them, they cannot be recovered.

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": "create_monitor"
  }
}

Input Schema

Name	Required	Description
`name`	No	Display name, not treated as identifying.
`public`	No	Whether /v1/monitors/:id/status and /s/:id are public.
`min_gpu_pct`	No	Optional GPU offload floor (0-100]. Alerts 'slow' when Ollama runs a model mostly on CPU.
`webhook_url`	No	Optional https:// webhook for alerts.
`grace_seconds`	No	60-86400, default 300.
`expected_model`	No	Optional Ollama model that should be loaded (e.g. llama3.1:70b). Alerts 'slow' when a different model is loaded instead.
`slow_tps_threshold`	No	Optional tokens/sec floor.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 4, 2026

addedInput schema / properties / expected_model

Added value: +{
+  "description": "Optional Ollama model that should be loaded (e.g. llama3.1:70b). Alerts 'slow' when a different model is loaded instead.",
+  "type": "string"
+}

Changed1 schema field changedOct 22, 2026

addedInput schema / properties / min_gpu_pct

Added value: +{
+  "description": "Optional GPU offload floor (0-100]. Alerts 'slow' when Ollama runs a model mostly on CPU.",
+  "type": "number"
+}

First observedOct 16, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare non-readOnly, non-destructive, non-idempotent, so the safety profile is covered. The description adds genuinely non-obvious behavior: the response contains ingest_token and manage_token returned exactly once and unrecoverable, which tells the agent this is a one-shot provisioning step with irreversible loss on failure. It omits whether creation requires auth despite the 'anonymous' label and whether repeated calls create duplicates, which non-idempotent implies but doesn't confirm.

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?

Two sentences, no filler. The critical, easy-to-miss fact (tokens are returned once and cannot be recovered) is placed in the second sentence where it reads as an imperative warning rather than being buried.

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 compensates by naming the two fields returned. For a zero-required-parameter creation tool this is nearly complete; the remaining gaps are whether the call is authenticated, what defaults apply when all parameters are omitted, and whether a failed attempt still consumes the one-time token issuance.

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 description coverage is 100%, and every one of the 7 optional parameters carries its own explanation of format and effect, so the schema does the semantic work. The description adds no parameter detail at all beyond the word 'anonymous', so the baseline 3 applies.

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 ("Create a new ... monitor") and characterizes it as "anonymous" and tied to "Paw Pulse", which meaningfully separates it from update_monitor and delete_monitor in the sibling list. It stops short of naming or contrasting those siblings explicitly, so an agent infers the create-vs-modify distinction rather than being told.

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 verb: call this to provision a new monitor. There is no explicit when-to-use vs update_monitor guidance, no statement about whether an existing monitor could be reused, and no prerequisites or error conditions. The token-storage warning is operational guidance but about what to do after the call, not about when to call it.

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

All Paw Pulse 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.