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

Annotations only cover the coarse safety profile (readOnly=false, destructive=false, openWorld=true); the description goes far beyond by mapping error codes to outcomes and retry policy: wp_timeout/wp_unreachable means uncertain state so don't blindly retry, source_unreachable means nothing was created, too_large at 25 MB, and a warning-plus-success case for follow-up title/alt_text updates. It also discloses that alt_text is applied by a follow-up update and not echoed back.

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 the core verb and the either/or rule, then parameter and error guidance in compact form. Slightly repetitive — the 25 MB limit is stated twice — and dense enough that scanning is required, but nearly every sentence adds distinct operational value.

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 7-parameter, zero-required upload tool with no schema descriptions and no enums, this is the level of detail needed: input mode selection, extension/mime constraints, size limits, return shape, alt_text verification path via wp_list_media, and a retry-safety policy for ambiguous timeouts. The presence of an output schema doesn't make the error/retry disclosure redundant.

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 0%, so the description carries the full burden and does: it explains exactly-one-of source_url/file_base64, that filename and mime_type are derived from source_url, that filename must include an allowed extension for base64 uploads, that mime_type is recommended, and that workspace is optional when only one workspace exists. All seven parameters are semantically covered.

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 ('Datei in die WordPress-Medienbibliothek hochladen') and immediately splits the two mutually exclusive input modes (source_url vs. file_base64) with 'Genau eines angeben'. Nothing about the tool's identity is left to inference.

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 when-to-use rules for each mode: source_url when the file lives online, file_base64 only for small agent-generated content, plus the crucial negative constraint that chat attachments and customer-local files cannot reach the server. It even includes the concrete Google Drive direct-link recipe and warns against the share link, which is precisely the failure an agent would otherwise hit.

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