execute_command

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

With no annotations provided, the description carries the full burden. It adds useful behavioral context: commands run synchronously and wait for completion. However, it does not disclose potential side effects (e.g., commands can modify the filesystem), permission requirements, blacklist constraints, or output size limits. The description is not misleading but leaves significant behavioral aspects unrevealed.

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 reasonably sized but includes redundancy: the top-level description and the schema description are near-identical, and 'Common uses' plus 'Keywords' overlap heavily. The Chinese translation doubles the length, which may aid multilingual users but is not strictly concise. It is front-loaded with the core message, yet the keyword list and repetition make it less efficient than it could be.

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 (4 params, output schema present), the description covers the essential context: execution model (synchronous), common use cases, and an explicit exclusion. The schema provides parameter details and the output schema covers return values, so the description does not need to explain those. It lacks mention of sandbox/permission constraints, but overall it is sufficiently complete for an agent to understand when and how to use the 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 description coverage is 100%, and the schema itself provides detailed parameter semantics (e.g., args as separate list elements, timeout meaning, work_dir behavior). The main description does not add parameter-level information beyond what the schema already states. Therefore, the baseline score of 3 applies; the schema handles the heavy lifting and the description offers no additional clarification.

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 shell commands synchronously and returns output. It specifies common use cases (git, npm, Python scripts, build tools) and explicitly differentiates from file operations, making its purpose unambiguous. The synchronous nature also distinguishes it from the sibling execute_command_async.

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 provides clear usage context: 'Use for running CLI tools, build scripts, version control, package managers' and lists examples. It also gives an explicit exclusion with a pointer to alternatives: 'Do NOT use for file operations - use dedicated file tools instead.' However, it does not explicitly mention the sibling execute_command_async for background execution, even though 'synchronously' implies it. So it has clear context and one explicit alternative, but not full alternative coverage.

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