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

Annotations give readOnlyHint=false and idempotentHint=false, but the description adds the critical non-obvious behavior: the source must be uploaded via this path and its key prefix is validated, plus the 2GB size cap. It doesn't cover URL expiration, so not a full 5.

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 dense sentences, front-loaded with the action and the exact field names to use (uploadUrl, r2Key), with the caveat parenthetical in the right place. No waste.

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?

No output schema exists, so the description correctly names the return values an agent must use (uploadUrl and r2Key). It links to the next tool in the workflow. Missing details like URL TTL or failure behavior, but the essential handoff is complete.

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 33%, and the description adds the practical 2GB size ceiling that constrains fileSize. It does not clarify fileName/fileType semantics beyond what the schema shows. Baseline for partially documented params, with one useful added constraint.

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 a presigned PUT URL for an AI Edit source video. Names the downstream sibling create_ai_edit and its own upload flow, distinguishing it from generic upload siblings like create_upload or swap_upload.

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 sequence: get URL, PUT bytes to uploadUrl, then pass returned r2Key to create_ai_edit. Also gives a constraint (source must be uploaded this way; key prefix validated) that tells the agent when not to bypass this tool.

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