get_function_calls

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

With no annotations provided, the description carries the behavioral burden and does disclose several non-obvious traits: the traversal is exactly one level deep (not recursive), indirect calls are included and flagged via direct=false, and offset/limit are applied per list rather than across the whole result. It does not state that this is a pure read with no side effects, but the added depth/indirection/pagination context is genuinely valuable.

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 with zero filler. The core identity ('function-level call graph, one level deep') is front-loaded, followed by the definitions and the pagination caveat in descending order of importance.

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?

An output schema exists, so return values need no explanation, and the description covers the aspects an agent actually needs to invoke it correctly: traversal depth, indirect-call handling, direction semantics, and per-list pagination. Nothing material is missing for a read-only graph query.

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, and it does add real meaning: it explains the direction semantics via the callers/callees definitions, clarifies that indirect calls surface as direct=false, and specifies that 'offset/limit apply to each list separately' – a behavioral detail the bare integer schema cannot convey. The address parameter is left implicit, which is the only notable gap.

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 gives a specific verb+resource (function-level call graph) and precisely defines the two result sets: 'callers are call sites that reach this function' and 'callees are calls made from anywhere in its body'. This is clear enough that an agent understands what it retrieves, though it never explicitly distinguishes itself from the many sibling xref tools (get_xrefs_to, get_function_xrefs), so it falls short of a 5.

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 when-to-use or when-not-to-use guidance, and no alternative is named despite several overlapping siblings (get_xrefs_to, get_xrefs_from, get_function_xrefs) that an agent could easily confuse with this one. Usage is only implied by the callers/callees semantics, leaving the selection decision to inference.

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