flow

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

With no annotations provided, the description carries the full burden and delivers: declares read-only safety, discloses the return shape (labeled nodes/edges), and — most valuably — states the over-approximation caveat that a missing path is not proof of absence. Also reveals the algorithmic behavior of bridging aliases through the heap.

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?

Three sentences with zero waste: what+relations, when+alternatives, return+caveat each earn their sentence. The read-only flag and core action are front-loaded for immediate orientation.

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?

Strongly complete for a complex graph-analysis tool with no output schema: selection guidance, safety profile, return format, and the key soundness caveat are all present. Minor gap: the interaction between limit=200 truncation and the 'missing path is over-approximation-safe' claim is not addressed.

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 covers 100% of parameters, so seed, limit, and format are already documented there. The description adds some semantic color (traversal over VALUE_FLOWS_TO + POINTS_TO, 'from a value/symbol'), but this mostly reinforces the schema's seed description rather than expanding on it. 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?

States a precise verb+resource pair ('Forward value-flow cone') and the exact graph relations involved (VALUE_FLOWS_TO + POINTS_TO), including alias-bridging through the heap. This sharply distinguishes it from the sibling set — sources_of (reverse direction) and reaches (yes/no witness) are explicitly named as different tools.

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?

Gives an explicit selection rule — 'Use it to answer where does this value go?' — and names the two closest alternatives with their exact conditions: sources_of for the reverse (what feeds a sink) and reaches for a yes/no witness. An agent can route correctly with zero inference.

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