edit_project

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

Goes well beyond the annotations by disclosing atomicity (all-or-nothing), the single-undo rollback model, and the complete action vocabulary including 'clear' and 'remove'. That rolls back the risk implied by destructiveHint=false for tools that can clear a project. It stops short of stating what happens on partial validation failure or what error shape returns.

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?

The critical guarantee (atomic, one undo step) is front-loaded in the first clause, then the action shapes are presented as a compact reference block rather than prose. Dense and reference-style, but every line maps to a real distinction an agent must encode.

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 mutating, non-idempotent tool with no output schema and zero schema coverage, the description covers the input grammar well but omits failure behavior, whether project state must be loaded first, and how this relates to plan_edit/describe_operations for resolving 'op' IDs.

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 0% and 'actions' is an untyped array of free-form objects, so the description carries the full burden and mostly meets it with a per-action grammar covering op/step_id/index/mask/opacity/blend/label and a mask example with all mask types. However the core 'params':{...} payload is left opaque and project_id/description are never explained, deferring to describe_operations.

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 ('apply edit actions') plus a scope guarantee ('atomically, one undo step'), which separates it from plan_edit and apply_preset. It does not explicitly name the sibling it supersedes, so an agent must infer the plan-then-apply pairing on its own.

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?

Usage is only implied: the atomic batch framing suggests this is the single mutation entry point to use after plan_edit, and the 'one undo step' phrasing hints at batching multiple actions. There is no explicit when-to-use/when-not guidance, no mention of prerequisites like an open project, and no direction to plan_edit or describe_operations.

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