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

Annotations already flag destructiveness (destructiveHint=true). The description adds useful behavioral context: it writes byte-for-byte and supports large files, implying chunking or multiple calls. It does not contradict annotations and provides extra detail about operation characteristics beyond the schema.

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 front-loads the primary use case and includes key differentiators (binary, byte-for-byte, large file support). It is concise with no redundant wording, and every clause adds value.

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 the main use case and notes large-file support, but does not explain the chunking protocol (e.g., whether to call multiple times or how to use mode for appending). The presence of an output schema and the schema's mode parameter partially mitigate this gap, but some ambiguity remains for complex scenarios.

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%, so all parameters (path, data, device, mode) are already documented. The tool description does not add any additional parameter-specific meaning, so a baseline of 3 is appropriate given the high schema coverage.

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 states a specific action (writing base64 data to a file) with clear scope (on a paired computer, byte for byte, including large files). It distinguishes from siblings like write_file and write_files by emphasizing binary content and chunking for large files, making its purpose unambiguous.

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 a clear trigger condition ('when the user needs base64 data written...') and mentions handling files too large for a single call, which guides when to select this tool. However, it does not explicitly mention alternatives or when not to use it (e.g., for text files), leaving some inference to the agent.

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