CodexPro Self Test

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

The description discloses key behavioral traits: it is local-only, does not touch source files, and can write/edit a single .ai-bridge file. It also mentions in-memory operations (Pro context bundle) without side effects. Annotations are all false, so the description carries the burden; it covers safety and side-effect boundaries well, though it omits exact return format or failure modes.

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 a single efficient sentence, front-loaded with the core verb and scope. It lists numerous checks without excessive detail, and every listed item adds informational value. Minor verbosity in the enumeration is acceptable given the tool's broad scope.

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 what the tool does but fails to mention what the tool returns — no output schema exists, so the description should hint at result format or interpretation. An agent has no guidance on how the diagnostic output is presented (e.g., JSON, plain text, exit codes) or how to handle failures. This is a notable gap for a diagnostic tool.

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 100% — every parameter has a description in the schema. The tool description does not add significant parameter-specific meaning beyond what the schema already provides. It references the `.ai-bridge` write/edit generally, but that maps to the `write_probe` parameter which is already described. Baseline of 3 is appropriate.

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 runs a controlled, local-only diagnostic and enumerates the specific checks it performs (modes, tools, workspace, skills, git, bash policy, Pro context). This distinguishes it from siblings like read, bash, or open_workspace by presenting it as a comprehensive self-test rather than a single operation.

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?

Usage context is implied: it is a diagnostic to verify environment capabilities. The description notes it avoids source files but does not explicitly state when to use it versus alternatives, nor does it provide exclusions or conditions. Some guidance is present, but it is not explicit about when an agent should invoke this over other tools.

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