get_imports_graph

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

With no annotations, the description carries the burden and does state the core behavior and output types. However, it leaves important behavior unspecified, such as whether traversal is recursive, how non-Python or unreadable files are handled, and whether the operation is read-only.

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?

Two sentences plus a param docstring, front-loaded with the primary action and outputs. No redundant wording or filler.

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?

For a one-parameter tool, the basics are covered (input directory and output format), and an output schema exists to define return values. Yet it omits traversal scope and edge-case behavior, and the absence of annotations leaves safety/prerequisite details unexplained.

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 has 0% description coverage, but the docstring provides direct semantics: target_dir is a path to a directory containing Python files. That fully compensates for the single parameter, though it does not add details like recursive traversal that might affect the parameter's meaning.

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?

Description states a specific verb+resource: scan Python files in a directory to build an import dependency graph, and names two concrete outputs (structured map, Mermaid diagram). This clearly differentiates it from sibling tools that analyze individual symbols, files, or docstrings.

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 scope 'all Python files in a directory' implies when to use it, contrasting with per-file or symbol-level tools, but there is no explicit when-not-to-use statement or named alternative. It also does not mention prerequisites like valid directory permissions or expected input type beyond a path.

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