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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds critical behavioral nuance: collections moved to another section survive, while those still in the section are deleted. This goes beyond the annotation and provides functional transparency about the blast radius. The confirmation requirement also adds context about the intended workflow.

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?

Two crisp sentences. The primary action leads, followed by the mandatory confirmation instruction, then the nuanced effect on collections. No filler or repetition. Perfectly front-loaded and efficient.

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 description covers the essential behavioral outcomes (what survives, what is deleted) and the workflow requirement (confirmation). With no output schema, return format is not needed. It does not explicitly state what happens if `confirmed` is false, but that is implied by the schema parameter description. Given the simplicity of the operation, this is nearly complete; minor gap is the lack of explicit error/edge-case handling.

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 50%: the `confirmed` parameter has a description, but `uuid` does not. The description says 'Delete a section,' implying that `uuid` is the section's identifier, which provides some missing semantics. It also reinforces the `confirmed` flag by saying 'Confirm with the creator first,' but adds little beyond the schema description for that parameter. The description does not fully compensate for the missing `uuid` documentation, so middle score is appropriate.

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 opens with a clear verb and resource: 'Delete a section.' It unambiguously identifies the operation and resource, and the additional detail about collections distinguishes it from delete_collection (which would delete collections). This is specific and non-tautological.

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?

The description gives a clear prerequisite: 'Confirm with the creator first,' and explains the conditional effect on collections, which helps the agent decide when to call this tool. It does not explicitly name alternatives, but the resource specificity and the destructive nature make the usage context clear. A slight miss is not stating when NOT to use it (e.g., if the section still contains collections that should be preserved).

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