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

Adds real context beyond the annotations: that the client must perform an HTTP PUT of raw bytes, that the tool is hidden from sandboxed clients, and that retries with the same idempotency_key return the original result. The retry-safety claim sits in mild tension with idempotentHint=false, so this is not a clean 5, but the disclosure is otherwise strong and not 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?

Five sentences, each load-bearing: purpose first, then eligibility, then the alternative, then retry semantics. No filler or restatement of the name.

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 agent still learns what is created, how the returned URL is used (PUT raw bytes), who may call it, and idempotency behavior. It stops short of describing the response shape or URL lifetime and does not fill the low-coverage parameter gaps, so it is not fully complete for a 9-parameter tool.

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 only 44%, so the description is expected to compensate. It only references idempotency_key in passing and says nothing about folder, brand_id, content_type, file_name, or how workspace_id interacts with the required-args rule, leaving most parameters underexplained.

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 compound verb+resource: creating a media record plus a signed Supabase Storage upload URL. It immediately differentiates itself from the sibling aidelly_upload_media by name, so an agent can route between them without opening either schema.

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 eligibility condition (clients with direct network access to Supabase storage, e.g. Claude Code or a local CLI) and an explicit when-not (browser-sandboxed chat clients block egress), then names the alternative tool for that case. This is exactly the when/when-not/alternative pattern.

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