list_devices

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

No annotations are provided, so the description bears the full burden of disclosing behavior. The verb 'List' implies a read-only operation, but the description does not explicitly state whether the operation is safe, requires authentication, has rate limits, or returns all devices vs. a paginated subset. It does disclose the optional filtering behavior, but for a simple listing tool the absence of any remark on side effects or response structure is acceptable, though not exhaustive. No contradiction exists.

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 extremely concise: one sentence stating the primary purpose and one line describing the optional parameter, followed by examples. It is front-loaded with the main verb and resource, and every sentence earns its place. No filler or redundancy.

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?

This is a simple tool with a single optional parameter and no output schema. The description gives enough to call it correctly: what it does, how to filter, and example values. It does not describe the return format, but for a listing tool an agent can reasonably assume a list of device objects. Siblings like get_state likely handle the per-device details, so the description is adequately complete for its simplicity.

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 input schema provides only the type and default for 'system' with no description (0% schema coverage), so the description must compensate. It does so by explaining that 'system' is an optional key and giving concrete examples ('lights', 'blinds', 'roomtemps'), which adds meaningful context beyond the bare schema. The explanation is clear enough for an agent to infer valid inputs, though it doesn't enumerate all possible system keys.

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 verb 'List' and the resource 'available myGEKKO devices', and notes optional filtering by system. This is easily distinguishable from sibling tools like get_state (which retrieves a state) and describe_capabilities (which describes capabilities). The purpose is unambiguous and specific.

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 tells the agent it can optionally filter by a system key, and provides examples of valid keys ('lights', 'blinds', 'roomtemps'), which gives some context on how to use the parameter. However, it does not explicitly mention when to use this tool instead of siblings like get_state or describe_capabilities, nor does it state any exclusions or prerequisites. The guidance is partial but not misleading.

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