get_change_impact

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

With no annotations, the description carries full burden. It explains the tool's behavior: enumerating exported symbols, resolving references, partitioning into test/non-test callers, and optionally including transitive callers. It also discloses the return structure (affected_symbols, test_callers, non_test_callers). No contradictions.

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?

Three sentences with no filler. First sentence states core function, second lists outputs, third gives usage guidance and transitive detail. Every sentence earns its place.

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 no output schema, the description covers main inputs, behavior, and output structure. It could optionally mention file path formats or error cases, but is sufficient for typical use.

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 0%, so the description must compensate. It explains 'changed_files' as a list of files and 'include_transitive' as second-order callers. It adds meaning by connecting them to the overall function ('resolve their references across the workspace').

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 enumerates exported symbols, resolves references, and partitions callers into test vs non-test. It uses specific verbs ('enumerate', 'resolve', 'partition') and identifies the resource (exported symbols in specified files). This distinguishes it from siblings like get_references or call_hierarchy.

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 explicitly says 'Use before editing a file to understand blast radius,' providing clear context. It also explains the optional transitive parameter. While it doesn't list when not to use or alternative tools, the purpose is specific enough to guide appropriate use.

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