list_devices

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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description adds critical behavioral detail: default thinning of format_detail and address fields, the specific effect of include flags, and the quirk that periodic_collection may be null for legacy devices and is returned as null rather than conflated with 'stop'. This is exactly the kind of non-obvious runtime behavior an agent needs to interpret results correctly.

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 moderately long but every sentence earns its place: purpose, permission, thinning defaults, flags, and a null-handling caveat are all packed into a clear structure with dash-prefixed bullets. The most important purpose statement is front-loaded, and there is no redundant or filler text.

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 the tool has 6 parameters, no output schema, and annotations that already cover safety, the description covers the essential behavior: data source equivalence, prerequisites, permission, filtering, thinned fields, and null semantics. Minor gaps include lack of explicit mention of pagination behavior or response structure, but the 'same info as web admin edit list' reference partially compensates for the missing output schema.

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 100%, so parameters are already documented. The description adds meaningful semantics by explaining the practical consequences of include_format_detail (hundreds of items per format) and include_alerts (includes email addresses), and by clarifying that group_cds supports OR filtering. It does not discuss page/page_size, but those are straightforward and already covered by the schema.

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 a specific verb and resource: 'テナントに紐づく地点（端末）の一覧を取得します' (retrieves the list of locations/devices linked to a tenant). It also distinguishes itself by stating it returns the same information as the web admin location edit list, and it references sibling tools list_tenants and list_groups for prerequisite IDs, clearly separating it from list_users, list_formats, and dashboard tools.

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 tells the agent to obtain tenant_id via list_tenants, and explains when to enable include_format_detail and include_alerts based on data volume needs. It also states permission requirements ('制限なし'), providing clear invocation context. It does not explicitly say 'do not use for dashboards' or name list_device_dashboards as an alternative, though the sibling names make that implicit.

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