points_to

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

No annotations are provided, so the description carries the full burden. It opens by stating 'Read-only', discloses result characteristics ('pointed-to objects with path evidence plus explicit unknowns'), and provides an important interpretative caveat: 'a missing edge is over-approximation-safe, not proof the pointer is null.' This goes well beyond the minimal safety statement and gives the agent meaningful behavioral context.

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, each earning its place: the first states the operation and result, the second gives usage direction and exclusions, the third explains output nuance and a safety caveat. The most critical information (read-only, purpose) is front-loaded.

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 2 parameters, no output schema, and no annotations, this description covers everything needed for correct invocation: what it does, when to use it, what it returns, and how to interpret edge cases. The parameter schema handles the remaining structured details, so nothing essential 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 100%, so the baseline is 3. The description reinforces the meaning of 'value' by framing it as 'a value may point to', but adds no concrete parameter-level details beyond what the schema already provides ('value name or graph node id'). The 'format' parameter is also already fully described in the schema.

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 specific verb and resource: 'Return the heap objects a value may point to through POINTS_TO edges — the alias set behind a pointer.' It clearly differentiates from sibling tools by explicitly saying 'not for callers (`callers`) or value-flow (`flow`/`reaches`)', so an agent can tell it apart without opening sibling schemas.

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 description gives explicit when-to-use guidance: 'Use it for pointer/alias follow-up', and explicitly names the alternatives to avoid: 'not for callers (`callers`) or value-flow (`flow`/`reaches`)'. This leaves no ambiguity about when this tool is the right choice.

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