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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: deletion must target an explicitly intended element, ambiguity must be resolved first, and simulated removal via hiding/resizing is forbidden. It does not address permanence or recovery, but the core behavioral pitfalls are disclosed.

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?

Two tight sentences: the first defines the action and its scope, the second defines the correctness constraint. No filler, no repetition of the title, and the constraint is front-loaded enough to be read before invoking.

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, non-idempotent mutation with full schema documentation and no output schema, the description covers the essential correctness requirement (unambiguous, explicit target) and one dangerous anti-pattern. It leaves out whether the session/design state reflows or whether an undo path exists, but the annotations already signal destructiveness.

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%, including the nested options object with elementIds, allText, allImages, and targetAreas, so the schema carries the parameter burden. The description adds nothing about which option to use (e.g., elementId vs. elementIds) and merely restates that 'selected elements' are supported. Baseline 3 applies when the schema is fully documented.

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 ('Delete') and a precise resource ('text/image element or selected elements'), which an agent can distinguish from sibling mutations like move_element or remove_background. It does not explicitly name a sibling alternative, keeping it just short of a 5.

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?

"Resolve an ambiguous target before deletion" gives a precondition, and "do not hide or shrink it to simulate removal" rules out a fake-delete workaround. However, it never says when to prefer a different tool (e.g., remove_background versus deleting an image element), leaving the alternative-selection gap implied rather than explicit.

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