gograph_errorflow

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

Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds important behavioral context: freshness checks, retry of CHA/SSA after source changes, and that it's heuristic without full SSA or data-flow tracking. This exceeds annotation coverage.

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 well-structured with sections but slightly verbose. It front-loads the core purpose and clearly separates usage guidelines and return information. Efficient but could be more concise.

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?

Despite no output schema, the description specifies what is returned (definition sites, return sites, propagation paths, test names) and explains edge cases (paths empty when no chain). It also notes the heuristic limitation. Complete for a complex analysis 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 100%, so baseline 3. The description adds nuance: 'query' is preferred over 'term', and explains the boolean 'no_tests' excludes test files. This provides helpful guidance beyond schema.

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 how a named error sentinel or string is defined, returned, and propagates up the call graph toward HTTP handlers or CLI entry points. It distinguishes from siblings by explicitly saying not for general upstream traversal (use gograph_callers or gograph_impact) and not for listing errors (use gograph_errors).

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?

Explicit WHEN TO USE section describes auditing a specific error end-to-end, and NOT TO USE section provides alternatives for general traversal and error listing. This gives clear guidance on appropriate usage.

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