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

Annotations already cover the read-only, idempotent, non-destructive profile, so the description's real value is the added 404 semantics: bytes not yet sent, past the 24-hour window, or belonging to another agent. That is genuine behavioral context beyond the structured fields, though it doesn't discuss return shape beyond the field list or any rate/consistency behavior.

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?

Two sentences, front-loaded with the operation and then the returned fields, with the error condition last. The opening 'Get an upload' largely restates the title, a minor redundancy, but nothing else is wasted.

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?

With no output schema, the description carries the burden of describing returns and does so by naming the key fields (type, size, SHA-256, expiry). Combined with the 404 conditions and fully documented params, an agent has enough to call it correctly, though a fuller return description would be ideal.

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 coverage is 100% — both agent_id and upload_id already document their UUID format and the exact 404/403 outcomes for foreign or missing resources. The description adds no parameter-level meaning beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb and resource ('Get an upload') and immediately enumerates what the stored upload contains — bytes type, size, SHA-256, expiry — which distinguishes it from write siblings like create_upload. It stops short of naming a near-alternative such as get_attachment, so sibling differentiation is only implicit.

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?

Usage is implied by the resource description rather than stated: the agent can infer it should call this to inspect a single known upload, but there is no explicit 'use this when… / use X instead' guidance against get_attachment or list_attachments. The 404 rules describe failure conditions, not when-to-use policy.

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