service_list

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful context beyond annotations: the swarm manager requirement, the desired-state semantics of the returned entries, the docker-mcp-server.managed label behavior for managed_only, and the return format—all useful for accurate invocation.

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 one-line purpose, followed by a compact paragraph of context and alternatives, then a clean 'args:'/'returns:' breakdown. Every sentence earns its place with no redundancy, and the formatting makes it easy to scan.

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 no output schema and zero parameter descriptions in the schema, the description covers all essentials: what it does, prerequisites, parameter semantics, and return structure (one full service document per service). Minor omissions include the filters object's value structure and error behavior on non-manager nodes, but overall it is sufficient for correct use.

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%, so the description fully compensates by documenting both parameters. It enumerates valid filter attributes (id, name, label, mode) and explains managed_only's label-based filtering and its combinability with filters. The only gap is the filter object's value format (e.g., exact key-value structure), which is not specified.

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 line 'List swarm services' is a specific verb+resource statement that clearly identifies the tool's function. It distinguishes itself from sibling tools by explicitly contrasting with service_ps ('lists a service's tasks') and stack_services ('groups services by stack'), and clarifies scope with 'One entry per service (the desired state).'

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 names two explicit alternatives with their distinct purposes: service_ps for task-level detail and stack_services for stack-grouped listing, implying when NOT to use this tool. It also states a hard prerequisite ('Must run against a swarm manager'), giving the agent clear operational context for invocation.

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