compile_cpp

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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds valuable context: code is not executed, diagnostics are bounded, and assembly differences are not performance measurements. This goes beyond the structured metadata.

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?

Three concise sentences, front-loaded with the core purpose, followed by a brief mechanism note and a critical caveat. Every sentence earns its place with no redundancy.

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 covers core behavior, output categories, and a key performance caveat. Combined with a rich output schema and annotations, it is largely complete, though parameter-level details are deferred to the schema.

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%, and the description does not explain parameters like compiler, filters, libraries, or window. It provides a high-level model by mentioning source bundles, virtual files, diagnostics, assembly, and optimization records, which maps to some parameters but leaves many unaddressed.

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 uses a specific verb ('Compile') and resource ('C++ source bundle'), and clarifies it does not execute the code. This clearly distinguishes it from sibling tools like compare_cpp or analyze_cpp.

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 implies usage for compilation tasks but does not explicitly state when to use this tool versus alternatives. It mentions that compilation tools transmit source to a backend, but lacks direct when/when-not guidance.

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