define_code

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

With no annotations, the description carries full burden. It describes input as bytes at addresses, output on success/failure, and references internal function 'create_insn'. However, it does not disclose whether the operation permanently modifies the database or if it is reversible, which is relevant for a mutation tool.

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 two sentences, front-loaded with the action, and includes essential output details. Every sentence provides necessary information without extraneous text.

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?

The description explains the purpose, when to use, and return format, which is sufficient for a tool with output schema. However, it has a slight inaccuracy (says 'convert raw bytes' but inputs are addresses) and does not mention database modification. Given the complexity, it is adequate but not complete.

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 coverage is 50%, so description must compensate. It adds context by mentioning 'raw bytes' and 'each given address' to clarify that 'items' provides addresses. The 'end' field is not explained beyond schema, but overall adds some value.

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 converts raw bytes to code instructions at given addresses, and specifies the return format on success and failure. It distinguishes itself from siblings like 'define_func' by focusing on instructions at addresses.

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 explicitly says 'Use this when IDA classified an instruction as data or failed to decode,' providing clear guidance on when to use. It does not mention alternatives or when not to use, but the sibling list implies alternatives like 'define_func'.

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