impact_surface

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

With no annotations provided, the description carries the burden of behavioral disclosure. It adds meaningful context: the output includes a completeness/risk summary, `distilled_records` are labeled unreviewed, capped at 2, and the cap is signaled in `completeness_and_caveats.truncated_sections`. This goes beyond a simple read-only description, though it does not explicitly state side-effect-free behavior or permissions.

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 three sentences, each earning its place: the first states the core purpose and scope, the second gives usage timing, the third discloses an important output caveat. It is front-loaded and free of filler.

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 (10 parameters, no output schema), the description provides a solid overview of what the report includes and a key caveat about `distilled_records`. It does not fully describe the output structure, but the schema fills in param details, and the description is sufficient for an agent to decide when and how to invoke it.

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 low (30%), so the description must compensate. It clarifies that the tool targets 'a symbol or path,' giving hints about the `symbol`/`query`/`id` parameters. However, it does not explain parameters like `limit`, `resolution`, or `allow_ambiguous`. The schema itself describes `include`, `worktree`, and `full_memories`, but the description adds only marginal param value beyond that.

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 a specific verb ('graph' / 'Pre-edit blast radius') and resource ('symbol or path'), enumerating the evidence included (callers/callees, tests, docs, git history, papertrail, memories) and the summary output. This distinguishes it from siblings like find_callers or trace_callees by bundling them into a pre-edit report.

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?

Explicit guidance is given: 'Run this before changing anything non-trivial.' This clearly indicates the primary use case. It does not explicitly name alternatives or when not to use it, but the 'before changing' context and the ability to narrow with `include` imply that focused tools may be used for specific needs.

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