Write upload content

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

Annotations already indicate idempotentHint=true and destructiveHint=false. The description adds valuable context: retries are safe, finalized files cannot be changed, and the tool does not publish by itself. This goes beyond annotations by clarifying the state machine and idempotency implications. However, it doesn't mention potential errors or failure modes, but the bar is lowered due to 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 but information-dense, with each sentence serving a purpose. It front-loads the primary action, then covers sequencing, chunking rules, retry safety, and post-upload steps without fluff. It is appropriately sized for the protocol complexity.

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 (chunked upload with sequential indexing, final flags, and post-upload steps), the description covers all essential aspects: ordering, size limits, idempotency, and next steps. No output schema exists, but the tool's return value is not critical for correct invocation; the description's focus on input protocol is sufficient.

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 baseline is 3. The description adds significant semantic context: it explains the chunking protocol (index starting at 0, max 256 KiB), the meaning of final (last chunk of every file, empty for empty files), and upload_id connects to upload_start. This clarifies relationships between parameters (index, final, base64) beyond their individual schema descriptions.

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 action: 'Transfer one file's bytes into a remote upload', specifying the resource (remote upload) and the context (after upload_start). It also differentiates from siblings by explicitly mentioning publish and update as subsequent steps, making it distinct from upload_start, upload_status, and upload_cancel.

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?

Explicitly states when to use it ('Use after upload_start'), how to use it (sequential chunks, index starting at 0, max 256 KiB per chunk), and what not to do ('finalized files cannot be changed'). It also names alternative tools (publish, update) for post-upload actions, providing clear routing among siblings.

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