il.rewrite.translate_identity

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

Annotations are completely absent, so the description carries the full burden for behavioral transparency. It fails to disclose whether the operation is read-only or destructive, what side effects occur (e.g., modifies IL state, requires specific permissions), or what happens with the callback. The phrase 'identity mapping callback' hints at a transformation that maps IL to itself, but this is not explained. With 0% schema coverage and no annotations, the description is severely insufficient for an agent to understand tool behavior.

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 extremely short (6 words), but this is under-specification rather than conciseness. While brevity is valued, every sentence should earn its place—this description fails to provide essential information. The structure is a single vague phrase, which is insufficient for an agent to understand the tool. A truly concise description would pack more meaning into a short space, not sacrifice 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 that this tool has 3 parameters (2 required), no output schema, and no annotations, the description is completely inadequate. The agent needs to know what 'IL' is, what 'translate' does, the purpose of 'identity mapping callback', and how to use the parameters. Without this, the tool is effectively unusable. The complexity is moderate (binary analysis intermediate language), but the description provides no assistance to an AI agent.

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 defines three parameters (level, session_id, function_start) but provides no descriptions, enums, or examples. Schema description coverage is 0%, so the description must explain these parameters. However, the description mentions none of them—not even that session_id identifies the analysis session or that function_start specifies starting point for translation. With a required 'function_start' parameter of mixed integer/string type, the agent needs to know whether it's an address or function name. The description adds zero value beyond the schema structure.

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 'Translate IL with identity mapping callback' is vague. It states 'Translate IL' but does not specify what IL refers to (likely Intermediate Language in a binary analysis context) or what 'identity mapping callback' means. Among sibling tools, there are several 'il.' prefixed tools like 'il.function', 'il.instruction_by_addr', and other 'il.rewrite.*' tools, but the description fails to distinguish what this specific translation does differently. The acronym IL is undefined, and 'translation' could mean converting IL to another form or rewriting instructions, leaving the purpose ambiguous.

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 provides no guidance on when to use this tool versus alternatives like 'il.rewrite.noop_replace' or other 'il.rewrite.*' tools. There is no mention of prerequisites (e.g., having an active session), context for identity mapping, or when translation is appropriate. The context signals show that 'session_id' is required, suggesting a session dependency, but this is not explained. Without usage context, an AI agent cannot determine when to invoke this tool.

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