function_call_graph

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

With no annotations provided, the description is the sole source of behavioral information. It only says 'local call graph', which hints at scope but leaves critical traits undisclosed: whether the graph includes calls to library/external functions, how dynamic dispatch is handled, whether it is bidirectional, and what 'local' exactly means. It also does not describe how the 'function_name' filter modifies the output (e.g., whether the graph is reduced to that function's immediate interactions).

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 very concise at one sentence and front-loads the key concept ('Local call graph'). It earns its place, but it is arguably too terse, providing no usage context or edge-case information. Still, for the purpose of stating what the tool does, it is efficient and well-structured.

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 the complexity of a graph-producing tool with no output schema and no annotations, the description is incomplete. It does not explain what the graph output looks like, how to interpret edges, or how the 'function_name' filter affects the graph. For an agent to invoke and use this tool correctly, significantly more context is needed, such as whether the graph is directed, whether it is limited to project-local functions, and whether it includes indirect call chains.

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%, with both 'name' and 'function_name' having clear descriptions. The tool description itself adds no parameter-specific meaning, but since the schema already covers parameter semantics, a baseline of 3 is appropriate. The description does not need to compensate for missing schema info.

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 clearly states the tool's function: 'shows which functions call which functions' in a 'Local call graph'. This includes a specific verb ('shows') and a clear resource ('call graph') with a scope qualifier ('local'). It is sufficiently distinct from siblings like 'function_callers' (which focus on one function) and 'module_dependency_graph' (which focuses on modules), though it does not explicitly name these alternatives to differentiate.

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 guidance on when to use this tool versus alternatives. It does not mention that it complements or overlaps with 'function_callers' or 'find_references', nor does it explain preferred scenarios (e.g., project-wide analysis vs. single-function lookup). Without such context, the agent has no basis for choosing this tool over others.

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