ck_execute_code

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

With no annotations, the description carries the full burden. It discloses defaults (Docker), denies specific capabilities (network, filesystem, secrets, shell, deploy), validates source first, and supports dry_run. This is substantial behavioral context, though it omits error handling or return 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 a single sentence that conveys all critical information: target (generated code), environment (non-local sandbox, Docker default), restrictions (denies list), validation, and planning mode. Every phrase earns its place; 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 key behavioral aspects but lacks detail on output/return values, error handling, or session correlation. Since there is no output schema, the description should explain what the agent can expect after execution. The schema's max_output_bytes implies captured output, but this is not clarified.

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 75%, so baseline is 3. The description adds an overview (e.g., dry_run for planning) but does not significantly enhance individual parameter meanings beyond what the schema already provides.

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 executes generated code only in a sandbox (non-local, defaults to Docker). It lists key restrictions (denies network/filesystem/secrets/shell/deploy) and features (validates source first, supports dry_run). This distinguishes it from sibling management tools like ck_goal, ck_fs_read, etc.

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 safe execution of generated code in a sandbox. It states 'only inside a configured non-local sandbox', which sets clear context. However, it does not explicitly mention when not to use it or alternatives, though siblings do not include another execution tool.

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