graph_impact

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

The description discloses key behavioral traits beyond the annotation: it walks only stated-fact edges, never guesses on same-name matches, reports refused guesses, and runs `git diff`. The annotation (readOnlyHint: false) already indicates it may not be read-only, and the description does not contradict this. It adds valuable algorithmic context that the annotation does not provide.

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 extremely concise, using a single lead-in sentence followed by two brief clarifications. It is front-loaded with the core purpose and includes no filler or repetition. Every clause contributes to understanding the tool's behavior and scope.

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?

Despite lacking an output schema, the description conveys the essential output (callers, dependents, test files) and the algorithm's constraints (stated-fact edges, refused guesses). It does not explain the `untested_only` parameter's behavior, but the schema covers that. For a tool with three parameters and a non-trivial purpose, the description is sufficiently complete for an agent to call 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 description coverage is 100%, so the schema already documents all parameters (diff, depth, untested_only). The description only indirectly references the diff parameter by mentioning `git diff`; it adds no new meaning for depth or untested_only. This is the baseline score when the schema carries the explanatory load.

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's function: it identifies what a diff can break by finding callers, dependents, and test files that reach changed symbols. It also distinguishes itself from likely siblings by specifying it walks only stated-fact edges, never guessing on name matches, and reports refused guesses. This gives a specific, actionable purpose that sets it apart.

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 does not provide any guidance on when to use this tool versus alternatives. It mentions that it runs `git diff`, implying it is for diffs, but it does not explicitly state scenarios or exclude other tools. No sibling references or conditions are given, leaving the agent to infer usage.

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