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

Annotations already declare destructiveHint=true, but the description adds material context beyond them: deletion is immediately irreversible, there is no trash, force=False fails with error 501, and timeout/unreachable responses leave the outcome uncertain so the agent should verify before retrying. That is exactly the operational knowledge a destructive tool needs.

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 the action and identifier source, then the irreversibility warning, then error handling, then the optional parameter. Every sentence contributes a distinct operational fact; nothing is padding or a restatement of the schema.

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 single-required-parameter destructive tool, the description covers the action, the identifier source, irreversibility, the unusable parameter path, error semantics for ambiguous failures, and the optional workspace scope. With an output schema present, return-value detail is correctly omitted.

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 must carry the burden and does: media_id is documented as a numeric ID with a specific {"error":"invalid_id"} failure mode, force is explained as default-true and mandatory-in-practice with a stated consequence for false, and workspace is explained as a customer slug that is optional when only one workspace exists.

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 ('Eine Datei aus der WordPress-Medienbibliothek löschen') and names the sibling tools that produce the required identifier (wp_list_media / wp_upload_media). An agent can distinguish it immediately from wp_list_media, wp_upload_media, or the non-WordPress media deletes in the sibling list.

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?

Makes clear where the media_id comes from and that force=False is not a viable path for media, which effectively tells the agent when not to use a parameter variant. It does not explicitly compare itself against other delete-media tools in the family (gbp_delete_media, strapi_delete_media), leaving that distinction to the tool name.

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