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

Goes beyond the annotations by disclosing that the call returns an API file picker or reuses an already-verified source, and by warning against shell-based uploads. The annotations already cover the safety profile (readOnlyHint=false, openWorldHint=true, destructiveHint=false), so the description's remainder is modest. There is mild tension worth noting: dedupe/reuse behavior is described while idempotentHint is false, though that is about effect repetition rather than a flat contradiction.

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?

Three front-loaded sentences with no filler: capability and preconditions first, return behavior second, routing rule last. Every clause carries operational information an agent needs.

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?

An output schema exists, so return values need not be spelled out, and the description covers accepted formats, the checksum precondition, and the fallback tool. What is under-covered is the scope of project_id and the size limits/constraints that make this a mutating staging step. Adequate for a five-parameter staging tool, but not airtight.

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 0%, so all five parameters rest on the description, which only loosely maps to them: media types match the media_type enum, and 'known size and SHA-256' imply size_bytes and sha256. The required project_id and the filename pattern/limits are never explained, and the 10 MB size ceiling is left to the schema. Partial compensation only.

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?

Names a specific action (prepare an upload) plus the accepted resource types (supplier PDF, requirements TXT, CSV, reference PNG/JPEG) and the precondition of a known size and SHA-256. It also implicitly distinguishes itself from open_design_source_upload, so an agent can tell what it stages versus what it opens. It stops short of saying what 'prepare' actually produces beyond 'the API file picker'.

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?

Gives an explicit routing rule: 'Prefer open_design_source_upload when no checksum is available', which names the sibling and the condition selecting it. It adds an operational constraint ('Follow returned upload state; never run shell uploads') that steers the agent's next step rather than leaving it to inference.

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