Device-Graph Identity Candidates

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

The description discloses the tool is 'Read-only' and returns 'empty when none are found.' It provides additional context beyond annotations by explaining the two cluster types and their confidence levels. No contradictions with annotations (readOnlyHint=true, destructiveHint=false).

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 long, front-loaded with the core function, and contains no redundant information. Every sentence adds 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?

Given no output schema, the description explains what is returned (clusters of end users with two types) and that it can be empty. This is mostly complete, though it could explicitly state the return type (e.g., a list).

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?

There are no parameters, and the schema coverage is 100%. The description implicitly clarifies that no input is needed, which aligns with the empty schema. No additional parameter semantics needed.

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 that the tool returns clusters of end users seen on the same device, distinguishing two types ('anon_bridge' and 'device_shared') with confidence levels. It also explicitly ties to the use case of finding merge targets, differentiating it from sibling tools like merge_end_users.

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 guides usage: 'Use it to find merge targets, then act with merge_end_users.' This provides clear context for when to use this tool vs. alternatives. It lacks explicit when-not-to-use scenarios, but the clear purpose makes the guidance sufficient.

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