predict_impact

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

With no annotations provided, the description effectively discloses that the tool is read-only ('Returns'), uses a specific algorithmic basis (graph coupling), and importantly notes it makes no LLM call. This adds behavioral clarity beyond the schema, though it could mention performance or permission needs.

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 two concise sentences that deliver essential information upfront: what it returns, how it computes, and a key differentiator (no LLM). Every word adds value, with no wasted space.

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 complexity of graph coupling and the lack of output schema, the description is mostly complete. It explains the methodology and result format, though 'modules' could be ambiguous. Overall, it provides sufficient context for an agent to use the tool effectively.

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?

Both parameters have full schema descriptions (coverage 100%), so the description adds no extra meaning for the parameters. The schema adequately defines 'file_path' and 'repo', and the description does not need to elaborate further.

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 specifies a clear verb ('Returns'), a precise resource ('ranked Markdown list of modules'), and a unique method ('graph coupling'). It distinguishes itself from siblings like 'explain_change' and 'get_symbol_context' by focusing on impact prediction with a non-LLM approach.

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 use for change impact analysis but does not explicitly state when to use it versus alternatives like 'search_context' or 'explain_change'. It mentions 'No LLM call' as a trait but lacks direct usage boundaries or exclusions.

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