impact_analysis

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds a scope statement ('across the whole repository') and the transitive nature of the walk, but says nothing about result size handling, the elisions mechanism, or performance characteristics. With annotations doing the heavy lifting, this is adequate but thin.

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?

Two tightly packed sentences with the purpose front-loaded and the operational instructions following. No filler and no redundancy.

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 6-parameter, all-optional read tool with no output schema, the description covers purpose, trigger timing, scope, and targeting-mode exclusivity, which is most of what an agent needs. It leaves the max_chars/elisions contract and the deprecation of the files parameter to the schema, which is acceptable.

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 baseline is 3. The description adds one genuinely useful constraint not in the schema — that targeting modes are mutually exclusive ('one way at a time') — but it omits max_chars and lists 'file paths' as a live targeting mode even though the schema marks files as deprecated in favor of entity_ids.

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 states a concrete verb and resource — 'walk the graph from a change to every entity it could affect' — which conveys transitive impact traversal rather than a single-hop lookup. It does not explicitly name or contrast with siblings like find_references or graph_neighborhood, so the agent must infer the distinction from the tool name alone.

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?

'Call it before editing, across the whole repository' gives a clear situational trigger and scope. 'Target it one way at a time' adds a usage constraint on combining targeting modes, but no alternative tool or when-not-to-use condition is named.

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