callers

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

With no annotations provided, the description carries the full behavioral burden, and it mostly succeeds: it discloses direct + indirect dispatch modes, the tagging scheme (direct | indirect(may_invoke|context|fn-pointer)), external stubbing filtering, and the effect of direct_only. It does not explain the output schema or rate limits, but for a read-oriented query tool the key behavioral contract is clearly given.

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 compact, front-loaded with the core purpose, and each meaningful sentence adds behavior or scope. The final fragment 'A jump move' is unclear and does not earn its place, making the description slightly less polished than it could be.

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?

Given no output schema, the description reasonably tells the agent what rows look like (tagged by call kind) and how to narrow behavior using direct_only. It could be more explicit about the exact return field names, paging behavior, or syntax for passing a symbol name, but the stated details are enough for an agent to correctly invoke the tool and interpret 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 description coverage is low (only format has a description), and the description adds meaning mainly to direct_only. The phrase 'Who calls this symbol' implicitly explains the required name parameter, and limit/offset are conventional with schema defaults; format is already described in the schema. This is adequate but not detailed, since direct_only-like semantics are not expanded for all fields.

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 opens with a concrete question, 'Who calls this symbol', and clarifies the exact scope: direct + indirect dispatch, with external stubs filtered. This differentiates it from sibling tools such as callees (which would be the reverse direction) and indirect_targets (which focuses on a narrower set of indirect resolution behavior).

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 explicitly tells the agent when to use the direct_only flag, saying it returns only resolved decl->decl calls, and it explains that external stubs are filtered by default. It does not explicitly name alternatives or exclusionary conditions, but the behavior contrast is strong enough for an agent to select between this and related caller/callee tools.

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