optimize

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

With no annotations, the description carries the full burden. It discloses that the tool returns an optimized IL with a list of applied passes, and that the output shape matches input. It does not mention whether the input is mutated or side effects, but the context implies non-destructive optimization.

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 concise with a clear docstring format: a single sentence for purpose, then Args and Returns sections. Every sentence adds value, with no unnecessary words.

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 (2 parameters, nested object, no output schema), the description covers all necessary aspects: input source, pass selection, return format, and relation to sibling tools. It is complete for an agent to select and invoke 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?

The description adds significant meaning beyond the input schema: 'il' is described as 'the IL tree produced by lift_handler', and 'passes' explains the canonical set and that pass names are C++ enum names. This compensates for 0% schema description coverage.

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's purpose: 'Run VTIL optimization passes over a lifted IL tree.' It includes a specific verb and resource, and distinguishes from siblings like 'lift_handler' and 'emit_pseudo_c' by focusing on optimization passes.

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 explains the input (IL tree from lift_handler) and the canonical passes, plus that the output is a drop-in replacement for downstream emit calls. It doesn't explicitly compare to alternatives like 'simplify_lifted_il' but provides sufficient context for proper usage.

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