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

With no annotations, the description carries the full burden and does well: it discloses sanitisation of markup, color-to-CSS-paint conversion tied to colorMode, and that ids become permanent once a block references them. It omits what a replace does to existing consumers, error behavior on invalid source combinations, and the return shape, which keeps it short of a 5.

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, then constraints, then rules. Dense but each sentence carries a distinct constraint. Slightly telegraphic styling ('Rules:', backticks, colons) costs a little readability but no sentence is wasted.

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?

A 9-parameter mutation tool with no annotations and no output schema is a demanding case, and the description covers source exclusivity, id semantics, color behavior, and a pointer to a contract doc. It stops short of stating return values or failure modes, leaving a modest gap.

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 78% (high), so baseline is 3, but the description adds real semantics beyond the schema: the one-of relationship between svg and fileKey+nodeId, the enumerated group values for id, and the colorMode default logic. That is meaningful added meaning over the field-level descriptions.

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?

Opens with a specific verb+resource+scope: 'Add an icon to the site library, or replace one.' It further disambiguates by naming the two mutually exclusive input sources and the id format, so an agent can distinguish it from list-icons, get-icon, and delete-icon without opening a 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 explicit routing and ordering rules: 'list-icons FIRST', 'read get-skill-doc {id:"icons-contract"} before the first call', and 'EXACTLY ONE source'. It also declares the permanence constraint on ids, which shapes when to be careful. This is unusually complete when/when-not guidance.

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