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

Annotations already mark destructiveHint=true, so the safety profile is known. The description adds valuable behavioral nuance: documents inside are not deleted, they lose the collection link unless reassigned via reassignTo. This goes beyond the annotation and clarifies the non-recursive nature of the deletion, which is critical for an agent to predict consequences.

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 two sentences with no filler. The core action is front-loaded, followed by the most important side effect. However, the first sentence 'Delete a folder' is slightly imprecise and could be tightened to 'Delete a document collection' for consistency. Overall, it is concise and structured well.

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 destructive tool with two parameters, one required, and no output schema, the description covers the essential behavior: what happens to documents when the collection is deleted. It also implies the optional reassignTo parameter. The annotations supply the destructive hint, so the description complements rather than repeats. No missing information critical for invoking the tool 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?

Schema coverage is 100%, so the schema documents both parameters. The description adds a sentence about reassigning documents, which directly relates to the reassignTo parameter, providing behavioral context but no additional syntax or format details. It slightly enhances understanding but the schema carries the main load.

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 states the action ('Delete a folder') and the resource (folder/collection), though 'folder' is imprecise given the tool name and schema use 'collection'. It distinguishes from other delete_* tools by specifying the resource type and adds a key side effect about documents retaining their workspace position. The purpose is clear enough for an agent to identify the target.

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 implies usage (when you want to delete a collection) but does not explicitly contrast with alternatives like delete_doc or update_doc_collection. It does not mention when not to use this tool, such as when documents themselves need deletion. The context is adequate but lacks explicit routing to or away from siblings.

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