trace_call_chain

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that traversal is BFS-based, that class/file nodes are automatically resolved to functions, and that output is an indented text tree. It also documents max_depth limits. While it doesn't discuss auth or destructive behavior (unnecessary for a read-only trace), it provides substantive algorithmic details beyond the tool's name.

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 a brief purpose statement, followed by Args and Returns sections. Every sentence adds value—there is no fluff. The front-loaded purpose sentence immediately communicates the core function, and the parameter details are formatted for easy parsing.

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 moderate complexity (graph traversal with special node-type handling), the description is complete. It covers the algorithm, input parameters with defaults, special cases for class/file nodes, and the return format. Despite an output schema existing, the description's note that the result is 'indented text' is sufficient for an agent to understand the outcome. No critical context is missing.

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 0% description coverage, so the description must fully compensate. It does: an Args section explains each parameter (start_node_id, max_depth, project) with types, defaults, and constraints (e.g., max_depth default 3, max 10). This greatly exceeds the bare schema definitions, providing clear semantics for all three 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's function: 'Trace the function call chain starting from a node (BFS on 'calls' edges).' It uses a specific verb ('trace') and resource ('function call chain'), and specifies the algorithm (BFS on calls edges). This distinguishes it from sibling tools like find_path or find_impact, which focus on different types of graph traversal.

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 implies usage by explaining how it handles different node types and parameters, but it does not explicitly state when to use this tool versus alternatives. There are no direct comparisons or exclusions (e.g., 'for impact analysis use find_impact'). Guidance is implied but not definitive.

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