object.describe

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description is not burdened with the full safety profile. The description adds a small amount beyond the annotations (maturity level L3 and that per-request argument checks plus session policy apply), but discloses little else about observable behavior, error conditions, or state impact. There is no contradiction with the annotations.

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 text is short and cleanly formatted, with a label:value structure and no wasted words. However, the brevity reflects under-specification rather than deliberate conciseness — the command name is restated and only a risk tag and a session-policy footnote follow, leaving little actual guidance for the agent.

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 output schema, annotations, and sibling context still carry the descriptive burden given the tool's complexity. The description omits the object-addressing semantics entirely: with required=[] and both name and objectId present, an agent cannot know whether the tool implicitly targets a selected object, accepts either selector, or requires objectId specifically. The description is too thin to support reliable invocation.

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 50%, covering the harness params (_requestId, _authorization, _transactionId) but leaving the two domain-relevant selectors (name and objectId) undocumented in the schema. The description does not compensate at all: it never explains whether name or objectId should be provided, whether both are accepted, or what agent should pass when no required parameters exist.

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 essentially restates the command name ('PartMe Blender Harness command `object.describe`') without defining the actual behavior: what properties or data 'describe' returns, or how this differs from sibling inspection tools like blender_mesh_inspect or blender_scene_inspect is never stated. The only substantive add is 'Risk: read', which is a behavioral label 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 when-to-use guidance is given: there is no mention of when to call object.describe versus the many inspect/list siblings (blender_modifier_list, blender_animation_action_list, blender_geometry_nodes_inspect, etc.), and no mention of prerequisites such as an existing object or active selection. The only requirements sentence covers session policy and argument checks, not usage routing.

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