List Running Commands

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

No annotations exist, so the description carries the full disclosure burden. It does well on output shape (scope, cluster/service/role/host, minutes running, stuck flag against stuck_minutes, deepest active subcommand stage) and sort order (oldest to newest), plus a performance warning for include_roles. It says nothing about permissions required, result volume, pagination, or behavior when no commands are running, which are meaningful gaps for an unannotated tool.

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?

Structure is good: scope first, then the operational caveat, then returned fields, then parameters. Every sentence carries information, though the parameter defaults are restated from the schema and could be trimmed slightly.

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?

An output schema exists, yet the description still characterizes the returned fields and their ordering, which is a bonus rather than a requirement. Combined with the level-scope caveat and the include_roles cost note, an agent has everything needed to call this correctly; only the sibling-tool routing is absent.

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 must compensate, and it documents all three parameters: cluster (default all), stuck_minutes (threshold for 'stuck', default 60), and include_roles (also queries each role, slower). The include_roles latency note and the stuck_minutes semantics add real meaning beyond the schema. It does not say what identifier format cluster expects (name vs. ID), which is the one remaining ambiguity.

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 ('Todos os comandos em andamento no CM') and delimits scope across all levels (global, Management Service, clusters, services, roles), which an agent can act on directly. It never distinguishes itself from the near-identical sibling list_active_commands or from get_command, so an agent choosing between them gets no help.

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 supplies a real usage rule: a restart initiated directly on a service only appears at the service level, so looking only at the cluster is insufficient — this tells the agent to query broadly. It also flags that include_roles is slower, which supports a cost-based decision. It stops short of naming alternatives or stating when-not to use it.

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