list_agents

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

With no annotations, the description carries the behavioral disclosure burden. It goes beyond a static listing by revealing that .env and GUI secrets are re-read on every call, that local agents have write restrictions, and that cloud/local connectivity affects workflows. A minor lack is not explicitly stating whether the call itself is side-effect free, though the framing strongly implies it.

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 dense and unusually long for a no-parameter tool, but every clause contributes either to what is listed, when to call it, or important runtime caveats. It is front-loaded with the inventory purpose, though the punctuation-heavy middle section is somewhat packed.

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 annotations, no output schema, and zero parameters, the description is remarkably complete: it names the full inventory, the trigger condition, the state-refresh behavior, and the limitations that affect backend selection. An agent has enough to call and interpret this tool 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?

The tool takes zero parameters, so there is nothing for the description to add beyond the schema. It instead compensates by detailing exactly what statuses and fields will be reported, which indirectly clarifies what the agent should expect from the call.

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 the specific verb 'List' and enumerates a precise resource set: agents, backends, workflows, allowlist directories, cwd, and runtime status. This distinguishes it clearly from the many sibling tools by establishing it as a discovery/inventory tool.

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 explicitly instructs the agent to call this before dispatching work and explains why: to pick a ready backend. It also gives concrete runtime exclusions and constraints, such as local-only write directories and cloud agents being unable to reach local vLLM, with suggested workflow alternatives.

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