change_impact

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

No annotations are provided, so the description carries the full burden. It does disclose the returned structure (changed, stale, where_used, ok) and that it is a pre-commit report, which implies a safe read, but it never explicitly states side effects, permissions, or performance/cost characteristics.

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?

Front-loaded purpose and a clean parameter/Returns breakdown, but the internal references (issue #142, C3, §9) add noise that an agent cannot act on, and 'where-used' in the opening muddies the distinction from the where_used sibling.

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?

No output schema exists, so the description must explain returns — and it enumerates each field with meaning, covering the essential contract. Parameters are also explained, so the definition is largely sufficient for a 2-param analysis 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 coverage is 0% (schema exposes only types), so the description must compensate — and it does: lockfile is explained as the dependency-graph path and changed as the ECO's affected item/component ids. This adds real semantic meaning beyond the raw string/array types, though the id format is not specified.

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?

States a specific verb+resource: an impact report over a lockfile graph for a set of changed items, computed before commit. It is reasonably distinguishable from the sibling where_used (this one is change-driven and pre-commit), though the heavy internal jargon ('§9 stale set', 'issue #142, C3') obscures rather than clarifies the core purpose.

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?

Gives timing context ('BEFORE a change is committed'), which implies when to call it, but never names alternatives such as where_used or lifecycle_classify_change, nor states when-not to use it. Usage is implied rather than prescribed.

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