select_similar

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

With no annotations, the description carries the burden and does well: it discloses the selection prerequisite, single-mesh scope, that the selection grows rather than being replaced, and the return shape. It stops short of stating whether the mesh must be in edit mode or what happens when nothing matches, which matter for a Blender mesh operator.

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 purpose followed by constraints, then Args/Returns blocks — good ordering with no wasted prose. The enum enumeration is long, but it is inherently necessary given zero schema coverage; only slight redundancy in 'Requires something to already be selected: it compares against that.'

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 3-parameter selection tool with an output schema present, the definition covers purpose, prerequisite, scope, every parameter, and a return summary. The remaining gap is mode/context requirements (edit mode, active object state) that govern whether the call succeeds.

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%, so the description must compensate, and it largely does: all three parameters are explained, the 22 enum values are grouped into face/edge/vertex families (information the flat schema enum does not convey), and threshold's 0.0–1.0 scale is given. It omits that type defaults to FACE_AREA and threshold to 0.

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?

Opens with a specific verb and resource ('Grow the current mesh selection to vertices, edges or faces that resemble it') and immediately names the sibling it is not ('it does not pick objects (see select_objects)'). An agent can distinguish it from select_all_geometry or select_by_axis without opening a schema.

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?

States the hard prerequisite ('Requires something to already be selected: it compares against that') and the scope exclusion ('Works inside one mesh; it does not pick objects'). Both when-to-use and when-not-to-use are explicit, with a concrete pointer to the alternative.

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