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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true. The description adds genuinely new behavioral context: edits are staged and require a publish step to go live, the ~3MB size cap for inline base64, and the recommended source format. It does not, however, describe what happens to a prior favicon on overwrite or error behavior.

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 target path, then packs the exclusivity rule, format guidance, staging model, scope, and a sibling pointer into a few tight sentences. No sentence is filler; the density is high without becoming unstructured.

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 an 8-parameter mutation tool with no output schema, the description covers the essential call mechanics (one-source rule, clear semantics), the staging/publish consequence, size limits, scope restriction, and where to get deeper reference material. Nothing an agent needs to invoke it correctly is missing.

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 100%, so the baseline is 3, but the description adds a real semantic constraint absent from the schema: exactly one source field per call, and clear:true overrides the others. It also clarifies svgContent is user-supplied markup that must not be fabricated and recommends a 512px square PNG/SVG.

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+resource ("Set or clear the site favicon") and names the exact storage location (ROOT.props.seo.favicon). An agent can distinguish this from sibling tools like upload_image or update_site without opening any 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?

Explicitly enumerates the mutually exclusive input modes (mediaId, imageUrl, svgContent, dataBase64, clear) and the rule "give exactly one source". It also bounds applicability ("Sites only") and routes to a sibling for more detail (get_style_reference({ topic: "media" })).

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