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

Annotations only say it is a non-destructive write; the description adds the real behavioral envelope: sign-in/owner authorization, a ~700 KB base64 payload guidance with a hard 1 MB request cap, an 8 MB REST ceiling, and that the call returns a url to reuse. These are constraints an agent cannot infer from structured fields.

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 authorization requirement and the core action, then escalates to sequencing, payload limits, and the REST variant. Dense but nearly every clause carries operational information; the REST details add length that a pure-MCP agent may not need.

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?

With no output schema, the description still tells the agent what comes back (a url for use in uploaded HTML) and covers auth, size ceilings, and sequencing. The remaining gap is that it never clarifies which of the three parameters are optional for the MCP path when 0 are required.

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 0%, so the description must carry meaning, and it does for two of three params: file_type is enumerated as JPEG/PNG/WebP and file_base64 gets a size expectation. However, file_name is only mentioned in the REST/query-string context, leaving its role in the MCP call (and its optionality, since 0 params are required) unaddressed.

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 ('Add one JPEG, PNG or WebP to the website photo library') and distinguishes itself from the sibling upload_site_pages by ordering and dependency. An agent knows exactly what this does without opening the 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?

Explicit when-to-use: every image in a design must go through here before upload_site_pages, including data: URIs embedded in the HTML. It also names the alternative path for large photos (public https URL placed directly in uploaded HTML) and the REST route, so the agent can route correctly.

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