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

Annotations only say readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=true; the description adds the non-obvious facts that the site fetches the download URL once, that bytes inside the reply are size-limited, and that the upload is gated on human approval in Royally so nothing changes until then. It stops short of describing what comes back (attachment ID / media item), which a destructive write tool should ideally state.

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?

Purpose and file-source selection are front-loaded in the first two sentences, with caveats following. It is dense but nearly every clause carries decision-relevant information, though the text is cut off mid-sentence at 'Pass if_exis…', leaving a visible fragment.

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 13-parameter, nested-object, approval-gated write tool with no output schema, the description covers input routing, limits, and the Royally gate well. The remaining gap is the response: with no output schema the agent must be told what a successful upload returns (attachment/media ID) to chain into wp_set_featured_image or update calls.

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 85%, so the baseline is 3. The description does add genuine guidance tying convert_to, max_width/max_height and max_kb to the goal of keeping the original file's download link, but most per-parameter meaning already lives in the schema.

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 a file to the media library') and immediately scopes accepted file types. It also names the sibling 'wp_upload_media_from_url' and distinguishes the two input paths, so an agent can separate it from other media tools 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?

Gives explicit routing rules: use `file` for chat-attached/generated files, `content_base64` only for small raw bytes, and wp_upload_media_from_url for already-hosted files. It also names a concrete exclusion (sandbox paths like /mnt/data/... have no download link, so ask the user to attach) and recommends image conversion at upload time instead of pre-editing.

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