Device-Graph Identity Candidates

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

Beyond the readOnlyHint annotation, the description discloses the return behavior (empty when none found), the two cluster categories with confidence levels, and the caution 'review only' for low-confidence clusters. This adds meaningful context that annotations do not convey.

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 two sentences, front-loading the core output (clusters of users on same device) and then adding types, confidence, empty behavior, and next-step guidance. Every word contributes value.

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 no-parameter, no-output-schema tool, the description fully explains what is returned (clusters, empty case), the semantics of each cluster type, and the intended next action. Nothing important is left unclear.

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 tool has zero parameters, so schema coverage is effectively 100% and no parameter descriptions are needed. The baseline of 4 applies; the description adds nothing beyond that, but nothing is missing.

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 returns clusters of ≥2 end_users on the same device, distinguishing two types ('anon_bridge' high confidence, 'device_shared' low confidence). It also names the follow-up tool (merge_end_users), making its purpose distinct from siblings.

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?

It explicitly says to use it for finding merge targets and then act with merge_end_users, providing clear when-to-use context. It lacks an explicit when-not-to-use or named alternative, so it doesn't fully earn a 5.

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