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

The readOnlyHint annotation already communicates that this is a safe read operation, lowering the burden on the description. It adds useful context by naming the event types (enter/leave/update) and the REST method/path, which goes beyond the annotation. However, it does not disclose result shape, pagination behavior, or default direction details, leaving some behavioral aspects to the schema.

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?

The description is a single efficient sentence plus an endpoint reference, with no filler or redundancy. It front-loads the core purpose (retrieve historical presence events) before giving the REST path.

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 historical lookup with 100% schema parameter coverage, the description is largely complete: it names the resource, event types, and endpoint. No output schema exists, but 'presence events' adequately conveys the return type for invocation purposes. It could mention pagination explicitly, but this is a minor gap given the read-only annotation and detailed schema.

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?

The input schema covers 100% of parameters with descriptions, so the baseline of 3 applies. The tool description restates that this is for 'a channel' but adds no new parameter-level meaning beyond the schema's already detailed start, end, limit, and direction descriptions.

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?

The description uses a specific verb ('Retrieve') and a specific resource ('historical presence events (enter/leave/update) for a channel'), which precisely identifies what the tool does. It also includes the REST endpoint, reinforcing the exact operation. The word 'historical' and the event types clearly distinguish it from sibling tools like ably_get_presence (current presence) and ably_get_channel_history (messages).

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 implicitly signals when to use this tool via 'historical presence events' versus alternatives like ably_get_presence, but it does not explicitly state when not to use it or name an alternative for current presence or channel message history. There is no explicit 'use X for current presence' guidance, so the agent must infer routing from the name and context.

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