Begin a chunked file write

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

Annotations already declare readOnlyHint=false, so write behavior is known. The description adds valuable beyond annotations: uploads expire after 30 idle minutes, per-file ceiling is 250 MiB, and an upload_id is returned. This contextualizes the operation's lifecycle without contradicting annotations.

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 compact yet information-dense. Each sentence serves a purpose: stating the trigger condition, outlining the workflow steps, and noting limits. No filler or redundant phrasing.

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 is part of a multi-stage process, the description explains the entire flow (begin → chunk → commit) and critical constraints. It also notes an upload_id is returned, and since an output schema exists, return-value details are not required. Context is complete for an agent to select and invoke correctly.

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?

The only parameter 'app' is fully described in the schema as 'the app this file will belong to' (100% coverage). Since the schema carries the full parameter meaning, the description need not add more. It does not provide extra parameter details, matching the baseline for high 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 clearly states the tool's purpose: 'Start a chunked upload for a file too big for file_write's single call.' It uses a specific verb and resource, and distinguishes from siblings by explicitly referencing the chunked upload workflow and naming file_write, file_write_chunk, and file_write_commit.

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?

Explicit when-to-use guidance is provided: 'for a file too big for file_write's single call.' It also maps the full sequence of operations: returns upload_id, use file_write_chunk to send bytes, then file_write_commit to name the file. Additionally, it includes expiration and size constraints that affect when to use.

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