impact

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

Annotations already cover read-only, idempotent, non-destructive. Description adds useful context about the algorithm (transitive call graph traversal) and result format (hop distances, tests), going beyond annotations without contradicting them.

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 tight sentences that front-load the core purpose and immediately differentiate from the sibling. Every phrase adds value; no filler or repetition.

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 adequately explains what will be returned (reachable symbols with hop counts and associated tests). Combined with full schema coverage of parameters, an agent has enough context to call 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 already describes all four parameters with full coverage. Description adds practical nuance for max_depth (tradeoff) and implies source disambiguation, slightly enhancing parameter understanding.

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 ('answer what breaks'), a resource (call graph of symbols), and output (transitive reachability with hop distance plus tests). Clearly distinguishes from sibling find_usages.

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?

Explicitly names when to use (before a risky edit) and when to use find_usages instead (direct one-hop). Also explains max_depth tradeoff between reach and noise.

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