nds_analyze_control_flow

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

With no annotations provided, the description must carry the disclosure burden. It reveals that the graph is 'bounded' and that calls are not traversed, which are key behavioral traits. However, it does not explain what happens when an entry point is not uniquely mapped, how bounds are enforced, or whether the operation is read-only (likely, but not stated). It also omits any error behavior or output structure.

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 a single sentence with no wasted words, packing a lot of specificity into a compact form. It is front-loaded with the main action and modifiers. It sacrifices some clarity for brevity, but remains efficient.

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 tool's complexity (10 parameters, no output schema, no annotations), a one-sentence description is insufficient. It fails to explain the meaning of parameters, the structure of the output graph, preconditions like 'uniquely mapped', or any side effects. The description only partially fulfills the information needed to use the tool safely and effectively.

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?

The input schema has 10 parameters with 0% description coverage, yet the description mentions none of them by name. Terms like 'one uniquely mapped entry point' are not tied to specific parameters (e.g., runtimeAddress or romOffset). The description adds virtually no meaning to help understand the parameters, leaving the agent to guess how to invoke the tool correctly.

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 uses a specific verb ('Build') and a clear resource ('direct-control-flow graph') with explicit constraints: 'bounded', 'from one uniquely mapped entry point', and 'without traversing calls'. This distinguishes it from sibling tools like nds_analyze_function (which likely follows calls) and nds_disassemble_range (which produces disassembly, not a graph).

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 phrase 'without traversing calls' implies the tool is for control flow analysis that stops at call boundaries, giving some sense of when to use it versus a call-graph tool. However, it does not explicitly name alternatives or provide guidance on when to choose this over related tools like nds_analyze_function or nds_discover_functions. Guidance is implied rather than stated.

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