Control GDB

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

Annotations cover the safety profile (destructive, idempotent, open-world), and the description adds real context beyond them: asynchronous execution, the 60-second heartbeat, retry semantics, and explicit capability limits (no raw MI/console, no multi-inferior). It does not explain what destructive actions affect or auth/permission behavior, leaving a small gap versus a 5.

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?

Four dense sentences, front-loaded with the core action, then retry, async, and limitation details in priority order. No wasted text.

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 repeated, and the description supplies the async/event-consumption and limitation context an agent needs to call correctly. It could be marginally more explicit about heartbeat timing behavior but is otherwise complete for a complex control 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 coverage is 80%, so the schema already documents owner, argument, debug_id, and request_id. The description reinforces retry semantics for request_id but adds little argument syntax or enum meaning beyond the schema, so 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+resource ('Execute one supported GDB action') and adds a secondary capability ('renew the 60-second debug heartbeat'). It distinguishes the event-consumption path by pointing at debug_events, though it does not clarify its boundary against debug_start/debug_stop/debug_bridge_* siblings.

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 operational context: renewal is the heartbeat action, retries reuse request_id unchanged, and stops must be consumed via debug_events rather than this tool. It lacks explicit when-not conditions or a direct comparison to sibling debug tools, keeping it at 4.

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