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

Annotations already declare read-only, idempotent, non-destructive, closed-world, and the description's 'Read-only' largely repeats that. It does add behavioral substance by disclosing what is returned per mode (needs_you, client modes, learned lessons, across_autopilot, last four runs), which matters because there is no output schema. Minor gap: no pagination or freshness/caching detail.

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?

Front-loads the core concept ('Autopilot's state') and then structures the two modes clearly. It is dense and somewhat run-on, but with no output schema each clause carries real informational weight, so little is wasted.

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?

Because there is no output schema, the description must explain returns, and it does so thoroughly for both modes while also covering the access pattern (read-only) and the alternative tool. An agent has everything needed to call it 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?

With schema coverage at 100% and one optional parameter, the baseline is 3. The description goes beyond the schema's 'leave out for all clients' by spelling out the distinct return shape of each mode, so the parameter's effect is fully meaningful rather than merely documented.

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?

States the resource exactly ('Autopilot's state') and distinguishes two operating modes (no client = all clients; client = one client) with what each returns. It explicitly names the sibling it is not ('For every change with its reason and measured result, use autopilot_log'), so an agent can separate it from autopilot_log without opening either schema.

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?

Gives explicit when-to-use triggers in natural language ('use for "what does Autopilot need from me"', 'what has Autopilot learned', 'does it need anything') and routes the change-history use case to autopilot_log. Nothing is left to inference.

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