gimp_apply_filter

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

With annotations already covering the safety profile (destructiveHint=false), the description adds real behavioral context: it respects the current selection, and 'non_destructive=True lo deja como filtro editable en vez de fusionarlo con la capa' explains exactly whether the layer is modified destructively. This is the key operational nuance an agent needs.

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-loads the purpose and the selection-respects note, then the examples and the non_destructive rule. The long filter catalog is verbose but each entry doubles as a usable operation/property example, so it largely earns its space.

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?

An output schema exists so return values need not be described, and the annotations plus the description's non_destructive explanation adequately cover behavior for a mutation tool. The only real gap is the undocumented image_id/layer_id targeting behavior.

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 0%, so the description must carry the load, and it does for the two hard parameters: it enumerates example 'operation' values and shows the property shapes for many of them (e.g. gegl:gaussian-blur {std-dev-x, std-dev-y}). It also explains non_destructive, though image_id/layer_id semantics (e.g. defaulting to the active image/layer) remain unexplained.

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+resource: 'Aplica cualquier filtro GEGL a una capa' (Applies any GEGL filter to a layer), with the scope qualifier 'respeta la selección'. It is clearly distinguishable from the info-only sibling gimp_filter_info and the adjustment sibling gimp_adjust.

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 clear usage context (applies a GEGL filter to the current/selected layer) and explicitly routes the agent to gimp_filter_info to discover a filter's properties. It stops short of stating when-not to use it versus alternatives like gimp_adjust or gimp_pdb_call.

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