ably_get_statsRetrieve message/connection/channel usage statistics for the app tied to the API key, bucketed by time. REST: GET /stats.
| Name | Required | Description | Default |
|---|---|---|---|
| end | No | End of range, ms since epoch (inclusive). | |
| unit | No | Bucket size: minute | hour | day | month. Default minute. | |
| limit | No | Max buckets (<=1000). Default 100. | |
| start | No | Start of range, ms since epoch (inclusive). | |
| direction | No | forwards or backwards (default backwards). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it read-only; the description adds useful context by scoping results to the API key's app, stating time-bucketing, and giving the exact REST endpoint. No destructive or unexpected behavior is hidden.
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?
One tight sentence with the key scope front-loaded, immediately followed by the concrete REST call. No filler or repetition of schema details.
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?
For a read-only stats getter with no required parameters and a fully described input schema, the description covers the essential scope and result substance. It does not describe response shape beyond usage statistics and buckets, but annotations and schema carry the rest.
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 coverage is 100% and every parameter already has a meaningful description. The tool description adds only general time-bucketing context rather than new parameter-level meaning, so it stays at the baseline.
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 names a specific verb (retrieve), a concrete resource (message/connection/channel usage statistics), and a clear scope (app tied to the API key). It separates this from account-level or channel-specific operations.
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?
The description implies this is for the current app's usage stats and mentions time bucketing, but it never states when to prefer it over ably_get_account_stats or any other sibling. No explicit alternatives or exclusions are given.
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.
Every tool targets a distinct resource and action: account-level stats, app-level stats, channel details, history, presence, presence history, service time, and each control-plane listing (apps, keys, namespaces, queues, rules) are clearly separated. The only potentially confusing pair is account stats vs app stats, but their descriptions explicitly differentiate account-wide vs API-key-scoped usage.
All tools use a uniform 'ably_' prefix followed by a consistent verb_noun pattern: get_ for single resources, list_ for collections, publish_message for the write action, and whoami for token details. There are no mixed casing styles or inconsistent verb choices.
Fifteen tools is within the ideal range and each one covers a meaningful Ably capability, from control-plane inspection to channel data retrieval and publishing. The count feels justified given the breadth of Ably's API surface, with no redundant or filler tools.
The read side is well covered: stats, channel details, history, presence, and control-plane listings all have dedicated tools, and message publishing provides one write path. However, there are no create/update/delete operations for apps, keys, namespaces, queues, or rules, so lifecycle management is largely absent and an agent could not perform common administrative workflows.