List assignments targeting All Devices

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds valuable behavioral context: it discloses pagination scope ('resultCount, pageSummary, and graphUsage describe only the current tool call; follow nextCursor for complete coverage'), the opaque nature of the cursor, and conditional fields ('application intent when available'). These details go beyond annotations and help the agent understand the paginated, per-call nature of results.

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 with no filler. The primary purpose is stated first, followed by a focused usage tip, then a concise explanation of pagination behavior. Every sentence carries meaning, and the structure is logical.

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?

The tool has 4 parameters (none required) and an output schema, so per the rubric we don't demand return-field explanations. The description covers the core function, filters (category), and pagination (cursor), which are the most critical for correct invocation. It omits explicit guidance on 'limit' and 'platform', which could be inferred but are not documented. Given the pagination behavior is clearly stated, the description feels fairly complete for an agent to use successfully, though a brief note on limit would round it out.

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 description coverage is 0%, so the description bears the burden of parameter explanation. It does clarify two of the four parameters: 'category' (via 'set category to application') and 'cursor' (via 'opaque continuation cursor' and 'follow nextCursor'). However, 'limit' and 'platform' are not explained at all—no mention of pagination size or filtering by OS. Thus, only partial compensation for the low coverage.

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: 'Lists policies and applications that directly target All Devices.' It clearly differentiates from siblings like list_all_user_assignments (targets users) and list_unassigned_policies, and even narrows scope to 'directly target' to exclude inherited assignments. This leaves no ambiguity about what the tool does.

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 provides one direct usage tip: 'For questions about apps assigned to All Devices, set category to application.' However, it does not explicitly state when to use this tool over the siblings (e.g., 'use this for All Devices, not for user assignments') or mention exclusions. The implicit scope is clear from the name, but explicit routing to alternatives is absent, so it falls at implied usage rather than explicit guidance.

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