secondary

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

With no annotations, the description carries the full burden and does meaningful work: it discloses that chains follow each layer's centre line, that the chain starts at the body-overlapping end and hangs from the nearest body bone, and that presets override defaults with n_bones 0 meaning 'use the preset'. It omits preconditions and whether existing chains are overwritten, but the mechanical behavior is unusually well specified for a mutation tool.

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?

It is front-loaded with the core purpose and the routing table is substantive rather than filler, so little is wasted. But the telegraphic slash-lists, arrow notation and run-on sentences make it hard to parse, and the preset wording ('presets {slot: ...} overrides; n_bones 0 = the preset's') is compressed to the point of ambiguity.

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 complex multi-step rigging operation with 7 parameters at 0% schema coverage and no output schema, the description is far richer than typical but still leaves gaps: two parameters (detail, exclude) are unexplained, preconditions are unstated, and the expected result of the call is not summarized.

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 partially does: it explains n_bones (0 = preset's), presets ({slot: preset} overrides) and by_shape (catch-all for any elongated layer, and the slot routing makes 'slots' inferable). But 'detail', 'exclude' and 'project' are never mentioned, leaving three of seven parameters entirely undocumented.

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 states a specific composite action: find strand-like layers and give each a chain along its centre line, a weighted mesh and Spine physics. The phrase 'in one call' implicitly distinguishes it from the granular siblings (add_chain, rig_mesh, rig_physics, rig_strand), though it never names them explicitly, and the bare name 'secondary' carries no meaning 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 conveyed indirectly through the layer-name routing table (hair/lock → hair, cape/cloak → cloth, etc.) and the note that by_shape catches any other elongated layer. However there is no explicit statement of when to choose this over add_chain/rig_mesh/rig_physics, no preconditions (project must already have a rig), and no when-not guidance.

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