analyze_cpp

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

Annotations already cover read-only, open-world, idempotent, and non-destructive behavior. The description adds valuable context: output is bounded, failure status is aggregated, static-modeling caveats exist, and assembly differences are not performance measurements. This goes beyond the schema and annotations, though it doesn't detail all edge cases.

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?

Two dense sentences pack the core purpose, constraints, and caveats without redundancy. The first sentence is front-loaded with the action and resource, and the second adds necessary context about transmission and a performance warning.

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 (8 parameters, including nested objects) and 0% schema coverage, the description is not fully complete. It covers the high-level functionality and key constraints, but does not guide parameter usage or reference sibling tools like search_analyzers for discovering analyzers. An output schema exists, so return details are not required, but parameter guidance is still lacking.

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 carries the full burden. It clarifies 'source' and 'files' (source and virtual files) and adds the critical 'up to four' constraint for analyzers, but it does not explain compiler, filters, window, libraries, compiler_arguments, or how to construct analyzer selections. Most parameters remain undocumented.

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 explicitly states the tool runs up to four selected Compiler Explorer analyzers in a single compile-only request, immediately distinguishing it from compile_cpp and compare_cpp. It also specifies the output format (normalized bounded per-tool output with aggregate failure status).

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 phrase 'compile-only request' provides clear context that this tool is for static analysis rather than execution, and the mention of 'selected analyzers' implies prior selection (likely via search_analyzers). However, it does not explicitly name alternatives or state when not to use the tool.

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