sharing_suspects

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

Annotations only declare readOnlyHint=true, so the description adds real value beyond them: 'Only counts and pseudonyms are returned' discloses the privacy-limited return shape, and 'Cheap: reads panel history, does not touch the nodes' discloses the cost/performance profile. It does not cover auth requirements or pagination, but the added behavioral context is substantive.

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?

Three tight clauses, front-loaded with the outcome and free of filler. Every sentence carries information: the detection heuristic, the return privacy, and the cost profile.

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?

With no output schema, the description responsibly states what is returned (counts and pseudonyms), and the two parameters are fully covered by the schema. It is complete enough to call correctly, missing only explicit alternative-tool guidance, which is a minor gap for a self-contained analytics tool.

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 100%, so minIps and records are already fully documented in the schema. The description only alludes to the concept of 'many different IPs' without adding format, bounds, or interaction detail beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb (find) and resource (clients who probably share their subscription), then spells out the two detection signals (IP/app diversity in recent requests and HWID device counts). An agent can distinguish this heuristic detector from the raw sibling getters like get_subscription_request_history or get_top_users_by_hwid_devices without opening a schema.

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 phrase 'clients who probably share their subscription' implies the use case (account-sharing detection), but no explicit when-to-use or when-not guidance is given, and no alternative sibling is named even though get_top_users_by_hwid_devices and get_subscription_request_history cover overlapping ground. Usage is inferable but not directed.

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