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

Annotations already convey readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context by defining what constitutes a 'link' (shared device, IP, session, or similar name/email/behavior), which helps the agent understand the semantics of the returned relationships beyond what annotations state.

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?

Two crisp sentences front-load the action and resource, then immediately provide the evaluative use case. There is no filler or redundant repetition of schema information, making it highly efficient.

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 simple one-parameter read-only tool, the description covers purpose, parameter semantics (via schema), and usage context. It does not specify the exact return format, but the description's explanation of relationship types gives enough operational insight for correct invocation, and annotations cover behavioral safety.

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% — the only parameter 'id' is described as 'Tracked identity id'. The description does not add further parameter-specific nuance, so the baseline of 3 applies because the schema already documents the parameter adequately.

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 uses a specific verb 'List' and a precise resource 'cross-identity relationships for an identity', then enumerates what those relationships are (shared device, IP, session, or name/email/behavior similarity). This clearly distinguishes the tool from siblings like get_identity or get_identity_history, which operate on a single identity or its history rather than its links to other identities.

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 states when this tool is useful: 'Essential for evaluating cross-identity (fraud-ring-style) analyzers'. This provides clear evaluative context for selection, though it does not explicitly name alternatives or state when not to use it, which would make the guidance more complete.

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