nds_correlate_stop_context

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so meaningfully: it explicitly states 'without resuming execution' and 'read-only Ghidra project', assuring the agent this is a non-mutating and non-execution operation. It also hints at a prerequisite ('already-current') for Ghidra enrichment. It does not describe the return value or failure modes, but the key safety-relevant behavior is covered.

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 dense sentence that front-loads the core verb and resource, then appends necessary qualifiers about Ghidra and non-resumption. It is efficient but somewhat jargon-heavy and could be slightly reorganized for readability. Every clause adds meaningful context, so it earns a 4 rather than a 3.

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?

This is a complex tool with 5 parameters, no output schema, and no annotations. The description explains the high-level purpose and non-resumption constraint but does not clarify what 'bounded canonical static evidence' means, what the tool returns, or how the parameters influence behavior. For an agent to invoke it correctly, significantly more detail is needed.

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 5 parameters with 0% description coverage, so the description must compensate. It only vaguely maps to parameters via phrases like 'optionally enriching from an already-current read-only Ghidra project' (suggesting includeGhidra/decompileGhidraFunction) and 'bounded canonical static evidence' (suggesting referenceLimit). Parameters such as timeoutMs and nearbyInstructions are completely unexplained. This is insufficient for a 5-parameter tool.

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 precisely states the tool's action: 'Correlate the current stopped server-owned DeSmuME ARM9 state with the exact launched NDS ROM and bounded canonical static evidence'. This clearly distinguishes it from sibling tools like desmume_capture_stop_context (which captures context) and nds_resolve_rom_offset (which resolves single offsets). The verb 'correlate' plus the specific resources involved makes the purpose unambiguous.

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 conveys clear usage context by requiring a 'current stopped' state and noting that the tool operates 'without resuming execution'. It also indicates optional use of an 'already-current read-only Ghidra project', suggesting when Ghidra enrichment is appropriate. However, it does not explicitly name alternative tools or state when not to use this tool, so it stops short of a 5.

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