gsd_debug

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does add one behavioral trait: 'persistent state across context resets', which informs the agent that state is retained across resets. However, it does not disclose potential side effects (e.g., whether it modifies files or external systems), permissions needed, or any other behavioral nuances, leaving a gap in transparency.

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?

The description is a single, front-loaded sentence that efficiently conveys the core purpose and a key distinguishing behavioral trait. There is no redundant or unnecessary information, and every phrase contributes to understanding the tool's function.

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?

Given the tool's simplicity (one parameter, no output schema, no annotations), the description is adequate but not fully complete. It states the core function and a key trait, but does not clarify the precise nature of the persistent state or what actions the debugging takes. For a simple tool, this is a minimum viable description, with room to add context about expected behavior or prerequisites.

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?

The schema has one parameter 'issue' with a description 'Issue description', and schema coverage is 100%. The tool description does not add any parameter-level information. Per the rubric, high schema coverage (100%) sets a baseline of 3 even without additional param info. The simple string parameter is adequately covered by the schema, so a 3 is appropriate.

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 'Systematic debugging with persistent state across context resets' clearly identifies the tool's purpose as a debugging tool, using a specific verb-like noun ('debugging') and indicating a resource ('issue') implicitly. It distinguishes itself from siblings by adding the unique trait of persistent state. However, it doesn't explicitly name the input resource (issue) or fully elaborate on the scope of debugging.

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 provides no explicit guidance on when to use this tool versus alternatives among the many gsd_* siblings. It only implies usage for debugging tasks with persistent state, but does not state exclusions, prerequisites, or mention alternative tools for other scenarios. This is minimal guidance at best.

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