get_flowchart

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

There are no annotations provided, so the description must fully disclose behavioral traits. The description states what the tool returns ('predecessors and successors for each block') and its role in analysis. However, it does not mention whether this operation is read-only (it likely is, but not confirmed), any potential prerequisites (e.g., the function must be decompiled or disassembled first), or whether it might be computationally expensive for large functions. For a non-annotated read tool, this lacks full transparency.

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?

At three sentences, the description is concise without being terse. The purpose is stated upfront, followed by specific output details, and ends with a relevance statement. However, the last sentence ('Essential for understanding branch logic') is slightly redundant but forgivable. No fluff or waste.

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 this tool (it involves retrieving control flow graphs, which are non-trivial) and the lack of annotations or output schema details, the description is incomplete. It does not mention the return format (beyond block edges), how blocks are identified, what 'basic block' means in this context, or whether the graph is returned as a data structure or just a textual representation. The presence of an output schema is noted (though its content is unknown), which could supplement this, but the description alone is insufficient for a tool that likely returns complex nested data.

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%, meaning the schema property has no description (e.g., no title or detailed params). The tool description adds a high-level purpose but does not clarify what the 'identifier' parameter should be (e.g., is it a function name, address, or index?). Without any param info in schema or description, the agent must guess. The baseline for 0% coverage is 1, but the description at least implies the identifier refers to a function, so a 3 is marginally justifiable.

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 that the tool retrieves the 'control flow graph' (specifically basic blocks and edges) of a function, which is a specific verb-resource combination. It also mentions the purpose ('Essential for understanding branch logic'). However, it doesn't explicitly distinguish this from sibling tools like 'disassemble_function' or 'decompile_function', which are also used for understanding function control flow, but at different levels of detail.

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 does not provide any guidance on when to use this tool versus alternatives like 'disassemble_range' or 'get_function_callers', nor does it mention prerequisites (e.g., that the function must be analyzed first) or when not to use it. The user is left to infer from the tool's name and purpose that it is for graph-level analysis, but no explicit guidance is given.

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