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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint false), so the description need not restate it, yet it adds 'Read-only' anyway. It goes beyond annotations by enumerating the exact state components returned, giving the agent a concrete expectation of what the operation exposes without any contradiction.

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?

A single sentence front-loads the subject ('The Discovery Autopilot's state'), then uses a colon-delimited list to pack five distinct pieces of information into a compact, scannable format. Every word earns its place; no filler or repetition.

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 the tool's simplicity — zero parameters, no output schema, and annotations already establishing safety — the description fully covers what an agent needs: it describes every category of state that will be returned (current on/off, offer, send counts, approval queue, recent activity). Nothing critical is left for the agent to infer.

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 tool accepts zero parameters, so there is no schema detail for the description to supplement. Per the baseline for 0-parameter tools, this dimension is satisfied: nothing is left ambiguous about inputs.

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 gives a specific verb and resource ('Get autopilot state') and then names every constituent of that state: on/off, commission offer, send count vs cap, approval queue, and recent activity. It clearly differentiates from siblings such as set_autopilot, approve_autopilot_action, and reject_autopilot_action by framing this as a read-only observation tool.

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 provides clear context that this is for inspecting the autopilot's current state, listing exactly what information can be learned from it. It does not explicitly name alternatives or state 'when not to use', but the read-only framing and the sibling tool names make the appropriate use case obvious without additional guidance.

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