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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description still adds substantial behavior: empty results are not failures, expired=true means the link lapsed while previously uploaded files remain visible, and {"error": "unknown_token"} means an unknown or >24h-expired token requiring a new link. These are exactly the states an agent would otherwise misread as errors.

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 purpose, then return shape, then error states, then parameters; nearly every clause carries operational meaning. Minor inefficiency: the return-shape enumeration partly duplicates the existing output schema, and parameter notes trail the error cases rather than sitting next to the inputs.

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?

Covers the full calling context for a read-only polling tool: where the token comes from, what each response state means, what to do on failure, and how the returned media IDs are consumed downstream. An output schema exists, yet the description's semantic gloss on 'uploaded is empty' is a genuine addition rather than repetition.

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: 'token' is sourced from strapi_generate_upload_link, and 'workspace' is a customer workspace slug that may be omitted when only one workspace exists. That resolves both the provenance and the optionality question the bare schema leaves open.

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: poll an upload link to see what a customer has uploaded. It is immediately distinguishable from strapi_generate_upload_link (creates the link) and from strapi_list_media (inspects the media library), both of which are named in the text.

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?

The workflow is explicit: take the token from strapi_generate_upload_link, poll this tool, and treat an empty 'uploaded' array as 'keep waiting' rather than an error. It also routes the agent for the follow-up case (use strapi_list_media(ids=[...], full=True) for Blocks rich-text images). There is no explicit 'do not use this for X' exclusion, 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.