hcl_backend_topology

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

Annotations already declare the non-readOnly, non-idempotent, non-destructive profile, so the description correctly spends its words elsewhere: connection-keyed session lifetime, singleton session limit, and the project-root sandbox on working_directory. It does not say whether `close` tears down topology state or just releases the connection, which is the one behavior an agent most needs before closing.

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?

Short, front-loaded, and the most decision-relevant facts (state-changing, singleton, open prerequisites) come first. Minor noise from markup artifacts (double backticks, bold markers) and a stray paragraph break mid-thought.

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?

An output schema exists, so return values need not be described, and the session lifecycle and its coupling to hcl_device_power are covered. The remaining gap is the meaning of `udp_port` and `project_name`, plus how working_directory is resolved against a project root.

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 0%, so the description must compensate and it only partly does: it explains the `action` enum and the `topology`/`working_directory` pair required by `open`. `udp_port` (default 10000) and `project_name` are never mentioned, leaving two of five parameters opaque and their relationship to working_directory unclear.

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 set (open/inspect/close) on a specific resource (backend topology session), and explicitly flags it as state-changing. It also distinguishes itself from the crop of stateless siblings by naming hcl_device_power as the consumer of the session.

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 concrete preconditions for the `open` path (needs `topology` and a `working_directory` inside a configured project root) and a hard constraint that only one session can exist at a time. It stops short of saying when to call `status` versus `close`, or what happens if you call open twice.

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