find_all_callers_recursive

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

Description fully covers behavior: BFS algorithm, deduplication (each caller appears once at shortest distance), default max_depth (5), performance scaling with call-graph fan-out, and inclusion of function-pointer edges. Since no annotations are provided, the description carries the full burden and meets it comprehensively.

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 and front-loaded with the most critical instruction. Every sentence contributes value—purpose, alternatives, algorithm, parameters, and performance. No wasted words.

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 complexity and the presence of an output schema, the description is very complete. It explains the algorithm, use case, alternatives, requirements, and performance characteristics. It leaves no gaps for a sophisticated 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 description coverage is 100% and each parameter already has a clear description. The tool description adds context like the default limit (50), BFS depth for max_depth, and auto-detection for project_root. Though the schema descriptions are already informative, the tool description reinforces usage and provides additional nuance.

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 finds all transitive C/C++ callers of a given symbol using the libclang call graph including function-pointer edges. It distinguishes itself from siblings like 'find_callers' and recommends against using 'ctx_callgraph(action="callers")'. This provides specific verb+resource+scope and sets it apart.

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 tells when to use this tool ('impact analysis') and when not to ('for a flat, single-level caller list use find_callers'). It also mentions the prerequisite of a reference index ('fw-context index'). This provides clear guidance on alternatives and conditions.

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