simulation.collision

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

With all annotations false, the description carries the burden of disclosing behavior, but it only contributes risk and maturity meta-information ('Risk: standard; maturity: L3') and a session-policy boilerplate. It does not state what scene state changes, whether an object must be selected, or what happens when collision is configured. The risk/maturity fields add minor context beyond the annotations but no real behavioral transparency.

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 appropriately short at three sentences and contains no padding beyond boilerplate. However, the front-loaded sentence repeats the command name already present in the title, and the only substantive content (risk/maturity) is not purpose-oriented. It is compact but mostly low-value.

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 7-parameter mutation tool with an output schema and a family of near-sibling simulation commands, the definition is far from complete — an agent could not determine the operation's effect, prerequisites, or parameter meanings. The all-false annotations provide no safety profile, and the description adds no operational detail. The presence of an output schema does not rescue this, since the operation itself is never explained.

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 only 43%, and the described parameters (_requestId, _authorization, _transactionId) are the boilerplate ones rather than the domain parameters. The description says nothing about name, objectId, or thickness, leaving the agent to guess their meaning and required format (objectId does have a regex pattern in the schema, but its role is unexplained). For a low-coverage schema, the description was required to compensate and did not.

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 only restates the command name ('PartMe Blender Harness command simulation.collision') and adds risk/maturity metadata; it never states a verb, resource, or outcome. An agent reading this cannot tell what the collision command actually does — add a collision object, configure a collision modifier, or run a collision simulation. This is a tautology of the title rather than a purpose statement.

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?

No guidance is given on when to use this tool versus the closely related simulation siblings (blender_simulation_rigid_body, blender_simulation_cloth, blender_simulation_soft_body, blender_simulation_quick_smoke). The only conditional language is the generic policy reminder ('Per-request argument checks and session policy still apply'), which says nothing about selection or prerequisites.

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