gradients_manage

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

Annotations only declare destructiveHint=true, so the description carries most of the burden. It adds genuine behavioral context by restricting the tool to typed gradients in <defs> and excluding free XML/CSS, which prevents misuse. However, it doesn't disclose the destructive scope of the delete/apply actions, the optimistic-concurrency role of expectedRevision, or any auth requirement on workspaceId.

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?

A single dense, front-loaded sentence with no filler; the scope constraint is placed last where it belongs. The only minor issue is that 'replaces' does not match the schema's 'update' action verb, which slightly muddies the mapping.

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?

The tool has an output schema, so return values need not be explained, and the input schema is fully covered. Still, for a multi-action mutation tool the description omits any guidance on action selection, revision-conflict handling, or target selection, leaving the agent to infer these from the oneOf branches.

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% and the schema is extremely detailed (patterns, enums for kind/paint/spread/units, oneOf variants). With the schema doing the heavy lifting, baseline is 3. The description's verbs loosely map to the action variants and it notes the linear/radial typing, but adds no syntax or format detail the schema lacks.

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?

The description gives specific verbs (creates, replaces, applies, deletes) and a specific resource (typed SVG linear/radial gradients in <defs>). An agent can understand the tool's remit clearly. It stops short of naming a sibling (e.g., mesh_gradients_inspect or defs_vacuum) to explicitly draw the boundary, so it does not reach 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?

There is no when-to-use or when-not-to-use guidance and no alternatives named, despite a crowded sibling set (patterns_manage, filters_manage, mesh_gradients_inspect). The only routing hint is the negative constraint 'without accepting free XML or CSS', which is a scope limit rather than usage direction.

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