Impact candidate slice

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

With no annotations, the description carries the behavioral burden. It usefully discloses that edges are 'observed' and that the result is a candidate slice, not proof of full blast radius, which is valuable honesty about limitations. However, it does not mention whether the operation is read-only, what the output shape is, or how budget-related parameters affect behavior.

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 two short sentences with no filler. The core action is front-loaded, and the second sentence adds an important scoping caveat without repeating schema information.

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 tool with seven parameters, no annotations, and no output schema, this description is not complete enough for confident invocation. An agent would need to guess the meaning of most optional parameters and the expected return structure, so significant context is missing.

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 0%, so the description must compensate, but it explains almost nothing about the parameters. It connects 'symbol' to the likely symbol_id usage, yet does not clarify direction, depth, max_nodes, max_tokens, or profile, all of which are non-obvious from names alone.

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 uses a specific verb ('traverse') and resource ('observed caller/callee edges from a symbol'), making the core function immediately clear. It distinguishes itself from siblings by framing the result as an impact slice rather than a proof or a generic symbol lookup.

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?

There is no explicit guidance about when to use this tool versus siblings like get_module_dependents or get_symbol_context. The caveat that it is 'never a proof of complete blast radius' implies a limitation, but it does not tell the agent when to prefer this tool or what alternative to use for stronger evidence.

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