Call graph

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

Goes beyond the annotations by disclosing the cost model and statefulness: 'one engine run per target, cached.' It also flags that truncation is surfaced in the result ('levels state what was cut'), which is important behavioral context for a bounded traversal. What remains unstated is timeout behavior and response shape, keeping it off a 5.

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 compact clauses with the primary capability front-loaded and the alternate mode immediately after. No filler. The trailing 'levels state what was cut' is slightly terse but still earns its place by explaining truncation reporting.

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?

This is an 8-parameter, engine-backed analysis tool with no output schema, so the description must carry more of the return contract. It hints at levels/truncation but never describes the node/edge structure returned, caching scope, or what happens when the path is not found. Adequate but with clear gaps for an agent composing results.

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 coverage is 75% and the schema already documents goal, root, maxDepth, maxNodes, direction, and targetId in detail. The description only loosely maps 'by depth and node count' onto maxDepth/maxNodes and adds nothing for timeoutMs. With the schema doing the heavy lifting, the baseline 3 is appropriate.

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?

Names a concrete resource (call-graph neighborhood around a function) and a concrete verb-like behavior (retrieve callers/callees to a depth, or shortest path root→goal). An agent can distinguish the two modes from the sentence alone. It does not compare itself to any sibling, but no sibling overlaps this domain (strings, bytes, export, etc.), so the omission is minor.

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 split between neighborhood mode and shortest-path mode is implied by the parenthetical and the 'or the shortest call path' clause, and the schema repeats the goal trigger. However, there is no explicit 'use this when…' guidance, no guidance on choosing direction/depth budgets, and no exclusions versus hexvero_provider_run or hexvero_analyze.

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