gograph_errorflow

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

Annotations already provide safety hints, but the description adds valuable context: it's 100% local, read-only static analysis with no side effects, no authorization/credentials needed, no rate limits, and zero destructive modifications. No contradiction.

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?

Well-structured with clear sections (BEHAVIOR & SAFETY, USAGE GUIDELINES, COMPLETENESS). Concise but includes essential information. Minor redundancy in behavioral section.

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 behavior, usage, and required parameter (though the required parameter is not in schema). No output schema, but description mentions return value. The missing 'function' parameter in schema reduces completeness.

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 100%, baseline 3. However, the description mentions a required 'function' parameter that does not appear in the input schema, which is misleading. The description provides no additional semantics beyond schema for the existing parameters.

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 clearly states the tool traces the flow and propagation of returned errors from a specific origin function. It uses a specific verb ('trace') and resource ('error flow'), and distinguishes from siblings like gograph_callers/callees.

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?

Explicitly states when to use (auditing error-handling completeness, locating unhandled errors, tracing failure modes) and when not to use (standard call graphs), directing users to alternatives.

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