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

With no annotations, the description carries full behavioral burden and does well: it discloses auth scope ('available to every authenticated user'), persistence behavior ('stored and recorded as an upload asset'), and an important host-dependent UI effect (renders as an interactive panel the user can act on). It omits rate limits, error cases, and whether re-uploads dedupe/overwrite, keeping it below the top.

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-loads purpose, then method, then downstream use, then UI caveat, in a tight sequence with no filler. The final sentence about the interactive panel is longer but earns its place by preventing a redundant list/table response.

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 4-param, no-output-schema mutation tool, the description covers storage, auth, method choice, size limits, downstream consumption, and return value ('the returned url can be used anywhere a media URL is accepted'). Only finer details like failure modes and idempotency are 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 value the schema lacks: a ~7MB practical ceiling for base64 (the schema states only a 200MB url cap) and a stated preference for url. It does not clarify contentType or fileName precedence beyond what the schema already says.

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 media to the user's Unsora library') and clearly distinguishes itself from generation siblings like create_image/create_video by describing an import path rather than a synthesis path. An agent immediately knows this ingests existing media, not generates new media.

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 preferred path ('Pass a public source URL (preferred) or a base64 payload for small files') which selects between the two input modes, and names downstream uses (create_post media, reference images, clipping input). It lacks an explicit 'when not to use' exclusion versus e.g. upscale_image or remove_watermark, so it stops short of a 5.

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