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

Annotations already establish that this is a safe, read-only, idempotent operation. The description adds meaningful behavior beyond that: the long-polling contract (wait up to 25 s) and the cursor-based incremental retrieval pattern. It does not cover error behavior or cursor expiry, but it adds real value over the annotations.

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 tightly written sentences with zero waste. The purpose is front-loaded, and the second sentence earns its place by explaining the cursor workflow. No redundancy or filler.

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?

With no output schema, the description usefully states that the initial response contains latest events and a cursor, and explains how to continue. It leaves out details like event object structure, limit interaction, and type filtering, but the schema covers those parameters and the core polling contract is complete enough for an agent to call the tool correctly.

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 description coverage is 100%, so the schema already documents all five parameters and the baseline is 3. The description adds meaning by explaining the interaction between after and wait: passing the cursor as after and waiting yields only what happens next, which is a semantic combination not fully spelled out in the individual schema 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 identifies a specific resource (the autopilot's event log) and enumerates what it contains: analyses, signals, position changes, actions. This is clear enough to distinguish it from a general log or positions tool, but it does not explicitly name or contrast itself with siblings such as autopilots_logs or get_autopilot_positions.

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?

It gives clear operational context for the two modes of use: omit after to get the latest events plus a cursor, or pass that cursor as after with wait to receive only subsequent events. It does not, however, mention when to prefer this tool over alternatives like autopilots_logs or get_autopilot_positions.

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