diff_impact

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

Annotations only declare readOnlyHint=true; the description goes further by disclosing output ordering ('removed/signature changes with callers outside the diff first'), tier grouping, and a hard output budget ('<= 2000 tokens'). This is meaningful behavioral context beyond the safety hint, though nothing is said about how tiers are defined.

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 with the core purpose and tightly packed with no filler; the token budget is stated last where it belongs. The telegraphic fragment style (parenthetical lists, semicolon-separated clauses) is dense but readable.

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 read-only analysis tool with no output schema and no annotation richness, the description covers what is returned, how results are ranked, and the size ceiling. It stops short of defining 'tier' or the exact result shape, but an agent has enough to invoke it correctly.

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%, so the description must carry the load, and it does explain base/head semantics (merge-base comparison like a PR; head is a ref defaulting to the working tree). The 'limit' parameter is left unexplained, so compensation is strong but not complete.

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-ish action (analyze what a change touches) and enumerates the resource precisely: symbols changed between base and head, callers outside the diff, dangling uses, importers. It is clearly distinguishable from hotspots or repo_summary, though it never names a sibling to route against (e.g., find_references overlaps with 'callers').

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?

Usage is implied rather than stated: 'Compares the merge base, like a PR' tells the agent the intent is diff review, and 'head: a ref, default the working tree' clarifies the default. There is no explicit when-to-use/when-not or alternative routing to siblings like find_references or file_outline.

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