modifier.add

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

Annotations exist (readOnlyHint=false, destructiveHint=false) but are uniformly false, so they say little; the description adds only generic metadata ('Risk: standard; maturity: L3') and does not disclose what happens on invocation—e.g., that a modifier type must be chosen, that an objectId is needed, or that the operation is transaction-bound. No contradiction with annotations, but no meaningful behavioral disclosure either.

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 entry is short and front-loaded with the tool name and risk level, so it is not verbose. However, it is under-specified to the point of emptiness: the two sentences spend their space on harness boilerplate rather than content that helps call the tool.

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?

The tool has 9 parameters, nested oneOf settings covering 7 modifier types, a replay-safety transactionId, and a large family of modifier sibling tools, yet the description says nothing about which modifiers are supported, how to target an object, or how this relates to begin/commit/rollback transactions. Even with an output schema present, the definition fails to provide the essential context.

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 description coverage is only 33%, so the description should compensate, yet it mentions none of the 9 parameters—not the required 'modifier' discriminant, not 'objectId', 'settings', or 'modifierName'. An agent gets no help selecting the correct 'settings' oneOf variant or understanding the required fields from the description itself.

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 says only 'PartMe Blender Harness command `modifier.add`' which restates the name/title, plus risk/maturity metadata; it never states what the tool does (adds a modifier to an object). An agent must guess the purpose from the name and its position among the modifier siblings.

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?

There is no guidance on when to use this versus sibling tools like blender_modifier_configure, blender_modifier_apply, or blender_modifier_list. The 'Per-request argument checks and session policy still apply' line is a policy constraint, not usage-selection guidance.

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