Skip to main content
Glama

warm_site

Warm (pre-cache) a list of same-origin URLs for one of your sites. Creates a warm run and returns its run_id. The run is asynchronous and takes seconds to minutes depending on the URL count, so follow it with list_warm_runs or get_run instead of assuming it finished. A site runs one warm at a time. Requires the boosts:write scope.

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": {
      "site_id": "<site_id>",
      "urls": "<urls>"
    },
    "name": "warm_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlsYesSame-origin URLs to warm. All must be on the site domain (or a subdomain).
regionNoOptional list of regions to warm from (defaults to ["fr"]).
site_idYesID of the site to warm (must belong to the API key).
variationsNoOptional request variations (e.g. device/header variants).
validation_ratioNoOptional: percentage of the warmed calls re-checked afterwards to verify the cache (min 5 per region). Defaults to 0 (no check). Each check is billed as a call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / validation_ratio
      Added value: +{
      +  "description": "Optional: percentage of the warmed calls re-checked afterwards to verify the cache (min 5 per region). Defaults to 0 (no check). Each check is billed as a call.",
      +  "enum": [
      +    0,
      +    1,
      +    10,
      +    50,
      +    100
      +  ],
      +  "type": "integer"
      +}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations at all, the description carries the full behavioral burden and discharges most of it: asynchronous execution, seconds-to-minutes duration proportional to URL count, a run_id handle, single-concurrent-warm semantics, and an explicit auth scope. What is left out is failure behavior (what happens to URLs that error or are off-origin) and whether base warm calls are billed, the latter only implied by the schema's note that validation checks are billed.

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?

Four short sentences, ordered by decreasing importance: what it does and returns, then how to follow up, then the concurrency constraint, then the auth requirement. No sentence duplicates the title or schema, and the async warning is placed before the scope note where an agent most needs it.

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?

For a 5-parameter mutation tool with no annotations and no output schema, the description supplies the return shape (run_id), the asynchrony and expected latency, the follow-up tools, the concurrency limit, and the required scope. Nothing critical to calling it correctly is missing, and the per-parameter detail is fully covered by the schema.

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%, so every parameter including region defaults, variation format, and the enums appearing in validation_ratio is already documented in the structured fields. The description only restates the same-origin constraint that the urls parameter already declares, adding no new syntax, bounds, or interaction detail. Baseline 3 applies when the schema does the heavy lifting.

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 definition states a specific verb and resource ('Warm (pre-cache) a list of same-origin URLs for one of your sites') and immediately states the observable effect ('Creates a warm run and returns its run_id'). An agent can distinguish this create-style operation from the read-only siblings (list_warm_runs, get_run, get_site) without opening any schema.

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 what to do after calling ('follow it with list_warm_runs or get_run instead of assuming it finished'), which is the main usage hazard for an async tool. It also surfaces two preconditions an agent would otherwise discover by failing: one warm per site at a time, and the boosts:write scope requirement. It stops short of naming when *not* to use it (e.g. an alternative for a single URL), but the sibling set contains no overlapping write path, so the gap is small.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources