patch.convert_to_nop

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description does not state whether the patch is reversible, if it requires specific permissions or session state, what happens on unsupported instructions, or what the tool returns. A mutation tool with zero annotation coverage needs much more detail.

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 short (4 words), which is appropriate for a simple concept, but it is under-specified. It lacks front-loaded critical details like what 'supported' means. It could be more concise if it were more informative without adding length; currently it wastes the opportunity to provide clarity.

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 (mutation tool, no output schema, two parameters with 0% schema description coverage), the description is incomplete. It does not explain return values, error conditions (e.g., unsupported instruction), or how the tool interacts with session state. The agent lacks enough information to use the tool correctly.

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%, so the description must compensate. It does not explain the meaning or expected format of 'address' (integer vs string) or 'session_id'. The agent has no semantic hints about how these parameters relate to the patch operation, such as what address types are valid or how session_id is used.

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 'Patch instruction to NOP when supported' identifies a verb ('Patch') and resource ('instruction') with a specific action ('convert to NOP'). It is distinguishable from sibling tools like 'patch.assemble' or 'patch.invert_branch', but the phrasing is slightly vague as it does not clarify what 'when supported' means or how the tool selects the instruction to patch.

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 gives no guidance on when to use this tool versus alternatives. Without specifying prerequisites (e.g., must be in a session, instruction must be patchable) or when not to use it, an AI agent cannot decide when this tool is appropriate over other patch operations like 'patch.assemble' or 'patch.skip_and_return_value'.

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