select_agent

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

With no annotations, the description carries the full burden. It discloses key side effects: the active agent shows in menu bar/settings, outgoing requests go there, and with exclusive mode other agents cannot change window/settings but can still read state and take screenshots. This is good transparency, though it doesn't explicitly state the default behavior when exclusive is false, which is slightly implied.

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 three sentences, each serving a purpose: the first states the core function, the second explains agent selection and its visual impact, and the third covers the exclusive option and a way to discover agents. It is front-loaded with the main verb and resource, and every sentence adds value with no fluff.

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 two-parameter tool with no output schema and no annotations, the description is remarkably complete. It covers all parameter behaviors, the user-visible effects, the exclusive mode restrictions, and where to find valid agent names. There are no significant gaps for an agent to misuse this tool.

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?

Although the schema already describes both parameters, the description enriches them significantly: it explains the three legal values for 'name' (specific agent, omit, empty string) and the nuanced effect of 'exclusive' (rejects changes from others, but allows reads/screenshots). This goes beyond the schema's simple field descriptions.

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 clearly states the tool's purpose: 'Make an agent the user's active one in Plonk.' It specifies the verb 'make' and the resource 'active agent', and differentiates from siblings like set_active by explaining the unique semantics of selecting, clearing, and exclusive mode.

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?

Provides explicit usage patterns: omitting 'name' selects the client itself, passing an empty string clears the choice, and 'exclusive' true adds extra restrictions. It also directs users to get_state to list agents, which is a helpful pointer. This is clear enough for an agent to know when and how to use it.

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