get_client_link_diagnostics

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

With no annotations, the description carries full burden and delivers: read-only, Fabric-only, in-memory selection from an upstream payload, passthrough of unknown/future fields, unchanged matching records, and clear failure for unmatched selectors. This is more than enough for an agent to predict side effects and edge cases.

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?

Front-loaded with a one-sentence purpose, followed by compact behavior and parameter blocks. The length is justified because there is no schema documentation and all sentences add operational detail.

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?

Covers purpose, constraints, parameter semantics, return passthrough, and failure behavior. It does not explicitly state the singular client_id return shape (single object vs list) or provide an example, but that is a minor gap given the detailed description.

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 0%, and the description fully compensates: host formats, site name/ID, client selector types, case/separator insensitivity, either-or rule, max 64 entries, list return, and failure behavior. Every parameter is given meaning beyond its JSON type.

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?

Opens with a specific verb+resource: 'Get first-class per-client link/policy diagnostics for one or more clients.' The resource and scope are clear, and the mention of reusing list_active_clients_stats' request distinguishes it from the sibling that returns all clients.

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?

Gives clear context: read-only, Fabric-only, and single vs multi-client selection with a strict either-or constraint. It names list_active_clients_stats as the underlying sibling request, which helps an agent place the tool, though it does not explicitly state when to choose this over that alternative.

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