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

Annotations only declare destructiveHint=true, so the description carries real weight: it enumerates the exact dependency classes that block deletion, states that the answer names which one, and spells out the consequence of forcing ('every place naming it then renders nothing') plus the `usedBy` field that lists them. That is disclosure well beyond the annotation.

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 action, then the refusal rule, then the force consequence, then the doc prerequisite — a logical order with no filler. The em-dash-heavy middle sentence is dense and takes a second read, which keeps it just short of a 5.

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 destructive two-parameter tool with no output schema, the description covers the blocking conditions, the override, the aftermath, the confirmation requirement, and the pre-call doc — the only return field an agent needs (`usedBy`) is even named.

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 meaning the schema lacks: `force` isn't just 'delete even while it is used' — it explains the downstream render failure and the `usedBy` report, and it conditions `force` on user confirmation.

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 with scope: 'Delete an icon from the site library and the project copy.' An agent can distinguish this from save-icon, get-icon and list-icons without opening any schema, and the description immediately names the effect on the project copy as well as the library.

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 when-not conditions (refused while an installed block, render bundle, icon field, options page choices, or live block version names it) and the escape hatch (force:true) with the caveat 'Confirm with the user before forcing.' It also imposes a prerequisite: read the icons-contract skill doc before the first call.

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