upload_media

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

Annotations declare destructiveHint=true, which is potentially confusing for an upload tool, and the description resolves it well: it explains the write counts against quota, does NOT publish anything, and that publishing happens in create_post. It also discloses the two-step delete path (first request previews and deletes nothing; second requires confirm plus that preview_id) and that in-use files are kept. Missing only finer traits such as idempotency/duplicate handling, though the annotation already states idempotentHint=false.

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?

Front-loaded with capability, then formats/limits, then input modes, then behavioral caveats — a logical order with no filler sentences. It is on the long side for a single tool and the delete flow is dense, but each block carries distinct information.

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?

For a 9-parameter tool with no output schema, the description covers return value (a reusable posterly URL), size/format limits, quota cost, the non-publishing safety story, multi-workspace scoping, and the destructive delete protocol. Nothing an agent needs to call it correctly is missing.

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%, so the baseline is 3, but the description adds real decision-level meaning the schema only partially conveys: it groups the parameters into three mutually exclusive input modes, flags base64+filename as preferred for chat images, warns never to guess file_path, and frames asset_id/confirm/preview_id as a preview-then-confirm delete protocol.

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 ('Upload an image or video to posterly storage and get a URL') and immediately names the sibling it feeds ('for create_post'), plus the two upload alternatives (create_signed_upload, create_media_drop) for the excluded PDF case. An agent can distinguish it from every sibling without opening a 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?

Explicit routing guidance: three input modes with a stated preference ('base64_data ... PREFERRED for images shared in chat'), file_path only when the user gives an explicit path, and url when you want to upload once and reuse. It also carves out exclusions (PDFs are not accepted here) and names the alternatives, plus notes when passing a URL straight to create_post/update_post is enough.

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