get_app_statsReal-time per-container resource stats (CPU / memory / swap usage) for an app. Scalingo API: GET /v1/apps/{app}/stats. Returns { stats: [...] }.
| Name | Required | Description | Default |
|---|---|---|---|
| app | Yes | The app name (e.g. my-production-app) or app id (app-…). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark readOnlyHint=true. Description adds context that stats are real-time, per-container, and specifies the types (CPU/memory/swap). It also cites the API endpoint. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no superfluous words. Front-loaded with the core purpose. API endpoint and return type are included efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description provides return format ({ stats: [...] }). It explains what stats are included and that it's per-container. Could mention pagination or error handling, but adequate for a simple read tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters with descriptions. The description adds minor context (e.g., API endpoint) but does not significantly enhance parameter understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it retrieves per-container resource stats (CPU, memory, swap) for an app. It uses specific language ('real-time per-container resource stats') that distinguishes it from sibling tools like get_app_logs or list_containers.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage when resource stats are needed but does not provide explicit when-to-use or when-not-to-use guidance, nor mention alternatives. It relies on the user inferring from the purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource or action: get_app vs get_app_logs vs get_app_stats are clearly different; list_addon_providers vs list_addons differentiate available vs provisioned. Mutation tools (restart, scale, trigger_deployment, set_variables) are unique. The fallback scalingo_request is a separate generic GET. No confusion between tools.
All tools use snake_case with a verb_noun pattern (get_, list_, restart_, scale_, trigger_, set_). The only exception is 'scalingo_request' which breaks the pattern, but it is clearly documented as a power-user escape hatch. Overall very consistent.
21 tools is well-scoped for a PaaS platform covering core resources like apps, deployments, addons, domains, env variables, and collaborators. It covers the essential operations without being bloated; each tool serves a clear purpose.
The toolset is heavily read-oriented; mutations are limited to restart, scale, set_variables, and trigger_deployment. Missing CRUD for major resources: no create/delete app, add/remove collaborators, add/remove domains, provision/delete addons, or update app settings. Agents will face dead ends when needing to perform writes beyond the few covered.