swarm_task_list

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

Annotations already signal read-only/non-destructive, and the description reinforces that with 'Read-only.' It then adds valuable behavioral detail: the call requires a swarm manager, non-managers get the daemon's refusal, and each result carries the full Spec/ContainerSpec. It could go further with pagination or result-volume caveats, but annotations already lower that burden.

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 front-loaded with a clear one-line summary and then a well-ordered set of differentiations, use cases, and caveats. Every sentence contributes useful information; there is no filler and no redundant repetition of input-schema content.

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?

Even without a schema-description coverage or output schema, the description states the return shape (`ID`, `ServiceID`, `NodeID`, `Slot`, `Spec`, `Status`, `DesiredState`), the filter behavior, the supported keys/enums, and the manager prerequisite. This is enough for an agent to invoke 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 0% schema-description coverage, the description carries all burden for the single parameter. It compensates thoroughly: it documents the `filters` dict, lists valid keys (`id`, `name`, `service`, `node`, `label`, `desired-state`), gives allowed desired-state values, and explains that omitting the filter returns every task.

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 opens with a specific verb, resource, and scope: 'List tasks across the whole swarm'. It immediately distinguishes itself from `service_ps` and `stack_ps`, so an agent can tell what this tool covers without inspecting the 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?

It gives explicit when-to-use guidance for whole-cluster questions, tells the agent when `service_ps` is the simpler alternative, and points to `swarm_task_logs` for reading a failing task's output. The filter documentation also maps to CLI equivalents like `docker node ps`.

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