list_devices

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

With no annotations, the description carries the burden and does so well for return-shape behavior: fields unavailable under the active auth mode appear as null rather than being omitted, so callers never branch on auth mode. It omits read-only/pagination/rate-limit disclosure, which is a gap for a list tool, but the null-filling contract is genuinely non-obvious behavioral information.

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?

Front-loaded with the purpose, then the normalization contract, then the parameter default. Two short paragraphs, no filler sentences. The detail on return shape is somewhat long for a one-parameter tool but each clause carries information.

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, so raw return values need not be explained, yet the description usefully adds the null-semantics contract that the schema likely cannot express. It leaves out pagination/result-size behavior and any explicit read-only statement, which are the only notable gaps for a zero-required-arg list 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?

Schema coverage is 0% (the schema only says 'Site Id', default null), so the description must compensate — and it does: site_id falls back to OMADA_SITE_ID or auto-selects when the controller manages exactly one site (legacy auth only). That is real added meaning beyond the schema, including an auth-mode caveat.

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?

States a specific verb and resource ('List devices on a site') and immediately qualifies the scope with the normalization guarantee. It does not name or contrast with any sibling (e.g. get_device_detail or get_clients), so the agent must infer boundaries itself, but the core purpose is unambiguous.

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?

Usage is implied rather than stated: the site_id defaulting rules (OMADA_SITE_ID, single-site auto-select) tell the agent it can call this with no arguments, which is useful context. However, there is no explicit when-to-use-this vs get_device_detail/get_clients guidance and no exclusions.

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