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

Beyond annotations it discloses that the operation is FREE, synchronous, and no paid job, plus the mutation semantics (omitted roles unchanged, null clears an override, none disables, tile roles override asset roles independently). This is rich, decision-relevant behavior that the readOnly/destructive/idempotent hints do not carry.

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 paragraph that front-loads the key facts (FREE, synchronous, owned revision), and each sentence carries distinct information. It is slightly run-on with several clauses packed together, but there is almost no filler.

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 highly nested, no-output-schema mutation tool, the description covers role semantics, coordinate frames, inheritance/override behavior, and the asset-vs-tile distinction. It is close to complete; only fine-grained shape-field semantics are left to the schema.

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?

With schema description coverage reported at 0%, the description must carry the load and does: it explains that coordinates are fractions of the full sprite/padded cell, radius is a fraction of width, and what omission/null/none mean per role. It does not detail the rect/circle/polygon/compound fields, which the schema itself partially documents.

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 names a specific verb (set), the resource (asset movement/hurtbox/hitbox collision roles), and the exact scope (an owned revision or collection tileIndex). It implicitly distinguishes itself from siblings set_asset_collision_body (named as the legacy fallback) and set_character_collision_roles (character vs asset).

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?

It gives clear conditions: hitbox requires explicit configuration on assets, hitboxFrames is unsupported on assets, and legacy collisionBody remains the movement/hurtbox fallback – effectively routing the agent away from set_asset_collision_body for hitboxes. It stops short of an explicit 'use X when / use Y when' statement with named alternatives.

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