tidal_autopilot

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

With no annotations, the description carries the full burden and does solid work: it discloses the non-obvious background behavior (each layer auto-switches variants on its own random timer, transform layers sometimes lay out), and clarifies the destructive-ish difference between pause ('keep playing') and stop ('hush everything'). It omits permission/auth needs and return shape details, but the core behavioral traits are well conveyed.

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?

Purpose is front-loaded in the first sentence, the mechanism follows, and each action is labeled with a colon in a compact list. It is dense but every clause contributes; minor tightening is possible but nothing 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?

For a tool with no output schema and no annotations, the description covers the mechanic and all four actions, including what status reports ('settings and how many layers are moving'). An agent has enough to call it correctly; only the exact return payload and any permission requirements remain unstated.

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 coverage is 75%, with the three numeric params already documented in the schema, so the field-level burden is mostly met by structured data. The description earns credit by explaining the required 'action' enum values that the schema leaves undescribed, but it does not clarify the units/ranges of maxSeconds, minSeconds, or layOutChance. Baseline 3 is appropriate.

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 opening sentence 'Keep layered channels evolving between turns' gives a specific verb-like behavior and resource (layered channels), and the mechanic is explained precisely. It does not name or contrast against siblings like tidal_status or tidal_hush, so an agent must infer differentiation, but the concept itself is unambiguous.

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 defines what each action (start/pause/stop/status) means, which functions as implicit usage guidance for the modes. However, it never states when to reach for this tool versus tidal_hush, tidal_status, or tidal_eval, nor any prerequisites/exclusions, so the routing guidance is only implied.

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