capability.describe

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds 'Risk: read' (duplicate of readOnlyHint), 'maturity: L3' (undefined), and a policy reminder, but these are not behavioral disclosures about what the tool does or returns. It does not contradict annotations, but it contributes little beyond them.

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 short, but its first sentence is a tautology of the title and wastes the opening. The remaining two sentences add non-essential context (risk, maturity, policy) but omit any substantive explanation. It is under-specification masquerading as conciseness.

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 10-parameter tool with an output schema, this description leaves the agent unable to determine what the tool does, what output it produces, or how to select it. It relies entirely on the name 'capability.describe' and provides no actionable context. An agent would have to guess or inspect other resources to use it correctly.

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?

Although schema description coverage is reported at 80%, most parameter descriptions are placeholders like 'See command validation; detailed type not yet audited', providing no real semantics. The single required parameter `id` is not described. The tool description adds nothing about parameters, so the meaningful coverage is effectively low.

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 `capability.describe`') without explaining what the tool does. It provides no verb+resource explanation, such as 'Describes a Blender capability' or 'Returns details about a specified capability'. Without that, an agent cannot infer the tool's function beyond its name.

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 alternatives like blender_capability_list or blender_session_capabilities. The only usage-related line ('Per-request argument checks and session policy still apply') describes constraints, not selection criteria. There is no mention of prerequisites, exclusions, or typical scenarios.

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