autopilot_cycle

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

Annotations declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, yet the description says the tool 'returns recommended actions', which reads as advisory and slightly at odds with the non-read-only, non-idempotent profile — though not a hard contradiction, since running a cycle can have server-side effects. The description does add genuinely useful context beyond annotations: the tier gate and the authority endpoint. It says nothing about side effects, rate limits, or whether repeated cycles compound state.

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 short and the operative sentence is clear, but a large share of the text is a bracketed metadata blob (capability key, tier, two raw API paths) that is opaque to an agent and front-loads information of low decision value. Front-loading the purpose sentence would have been better.

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?

Missing justification for score.

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 0% across four parameters, so the description carries the full burden — and it explains none of them. sessionId and sessionToken are self-explanatory by name and agentAddress has a regex pattern in the schema, but accountState is an unconstrained free-form object with no hint at expected shape, and the relationship between 'authenticated' and these credentials is not spelled out.

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 sentence 'Run one authenticated autopilot cycle. Returns recommended actions.' gives a specific verb and resource, and the phrase 'recommended actions' signals that this produces recommendations rather than executing them — an important distinction from execute_cycle_actions. However, it never names or contrasts itself with the many autopilot siblings (get_cycle_status, configure_autopilot, pause_autopilot), so differentiation is left implicit.

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 states a tier gate (pioneer_plus) and the need for authentication, but never says when an agent should run this cycle versus calling get_cycle_status or execute_cycle_actions, nor any preconditions or cadence restrictions. No when-not-to-use guidance is given.

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