blender_constraint_preset

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

With no annotations at all, the description carries the full behavioral burden. It says 'apply preset constraint setups' but does not disclose that this is a mutating operation on the armature, whether existing constraints on the named bones will be removed/replaced, whether the preset modifies bone transforms or only adds constraints, or what happens if bones are missing. The brief per-preset phrases hint at constraint types but not at side effects. No annotation contradiction exists because annotations are absent, but the behavioral disclosure is thin.

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 description is compact: one lead sentence plus six short preset labels. Every preset earns its place by conveying a distinct and informative behavior. The only inefficiency is that the preset names in the description partly duplicate the enum values in the schema, though the added behavioral gloss ('pole target', 'foot roll', 'mutual stretch-to', 'two-axis tracking') justifies the redundancy.

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 tool with three required parameters and a 100% schema coverage including nested bone mappings, the description plus schema covers the parameter contract well. However, there is no output schema and no annotations, so the agent is not told what the tool returns or whether it reports failures for missing bones — leaving a moderate gap for a mutating rigging operation. The rich sibling list makes the tool's niche clear but the absence of prerequisite info (armature must exist, bones must exist) is noticeable.

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?

The input schema already provides 100% documentation coverage, including a detailed per-preset breakdown of the bones object keys in the schema description. The tool description adds the preset taxonomy and per-preset behaviors ('IK with foot roll', etc.), which enriches the agent's understanding beyond the schema. Since baseline is 3 with full schema coverage and the description meaningfully supplements parameter meaning, a 4 is justified. It doesn't reach 5 because it doesn't describe axis format or angle units, leaving some semantics to the schema.

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 opens with a specific verb and resource: 'Apply preset constraint setups that require multiple coordinated constraints.' It then enumerates six named presets with concise behavioral summaries ('IK chain with pole target', 'two bones with mutual stretch-to'), which clearly distinguishes this tool from the single-constraint sibling blender_constraint_add. It could be stronger by stating the resource type (armature/bones) more explicitly, but the preset taxonomy gives solid differentiation.

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?

The description implies when to use it: when a constraint setup requires multiple coordinated constraints, which is effectively the exclusion condition versus blender_constraint_add (single constraint) and blender_autorig_preset (full armature rigging). It does not explicitly name those siblings or state 'use blender_constraint_add for single constraints,' but the contrast is embedded in the first sentence and preset list. The preset names with bone mappings also signal the intended use cases (IK arms, legs, pistons, wheels, doors, turrets).

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