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

Goes well beyond the annotations by disclosing a real transformation: SVGs with styles, classes or nested drawings get rasterized to a 2048 px PNG on a clear background, and the response says so. It also notes that URLs must be public and that Marsell fetches them server-side. It never explains the destructiveHint=true annotation — whether adding a logo replaces an existing one — which is the one behavioral fact an agent most 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-loaded with the core action and variants, then the SVG conversion caveat, then the upload-link escape hatch — a sensible order with no filler sentences. A few conversational asides ("the answer says so", "so nothing big passes through your messages") add warmth but little specification.

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 write tool with no output schema and zero required parameters, the description leaves two gaps: it never says at least one of url/data_base64 must be supplied, and beyond the SVG case it does not indicate what a successful call returns. The size limits and the shell-upload path are covered, so the picture is workable but incomplete.

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 100%, so the parameters are already documented; the description mostly restates them (public https url, base64 bytes, variants). It does add genuine meaning for `variant` by explaining Primary as "the main mark, the one Marsell uses" and for `label`'s purpose, but does not clarify that url and data_base64 are mutually exclusive inputs.

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 concrete verb and resource ("Adds a logo") and immediately enumerates the four variants (Primary, Light, Dark, Symbol) plus accepted formats. It also implicitly separates itself from add_brand_file/add_font/add_pictures by dealing exclusively with the logo mark, so an agent can pick it 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?

Gives an explicit routing rule for a common case: files on the agent's own machine should go through get_upload_link rather than this tool, which is a clear when-to-use-alternative statement. It does not say when NOT to use add_logo (e.g. versus add_brand_file for non-logo assets) or whether a logo can be added twice.

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