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

Annotations already declare readOnly=false, idempotent=true, destructive=false, so the safety profile is covered. The description adds real value beyond them: it discloses patch semantics (only changed fields are touched) and that null actively clears a field — a subtle, semi-destructive behavior — plus the images-only restriction on category.

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?

Three short sentences, front-loaded with the affected fields, then the calling convention, then the one field-specific constraint. No filler and nothing buried.

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 mutation tool with no output schema, the definition is adequate but stops short: it does not say whether the updated asset is returned, what happens on a missing or invalid assetId, or whether changes are immediately reflected in delivery URLs. Annotations cover reversibility and idempotency, so the remaining gap is moderate rather than severe.

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 only 25%, so the description carries weight and it names all three mutable fields plus the null-clearing semantics that the anyOf-null types only hint at. assetId is never mentioned, but it is the sole required param and self-evident as the target identifier.

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 (changes) and names the exact fields it mutates (filename, description, category), so an agent can distinguish it from websiteAssets_delete, _get, and _list. It does not explicitly contrast with websiteFavicons_set or other asset-adjacent siblings, but the resource+verb pairing is unambiguous.

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?

'Pass only the fields to change; `null` clears a field' gives solid how-to-call guidance and implies this is a partial-update tool. However, there is no explicit when-to-use vs. alternatives (e.g., delete-and-reimport vs. update) and no stated prerequisites such as the asset having to exist.

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