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

Annotations already mark destructiveHint=true and readOnlyHint=false, but the description adds meaningful context by naming what gets destroyed (stored outputs/classify group) and emphasizing irreversibility. This goes beyond the structured hints without contradicting 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?

One compact sentence delivers the action, scope, and consequence with no filler. The most important information ('Permanently delete') is front-loaded, and every word earns its place.

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?

Given the 100% schema parameter coverage, output schema presence, and annotations covering safety/destructiveness, the description is complete. It adds the critical deletion scope and irreversibility warning without omitting anything needed to invoke 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 description coverage is 100%, so the parameters are fully documented in the schema. The description does not add per-parameter meaning beyond the already-rich schema descriptions, so the baseline of 3 applies.

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 a specific verb ('Permanently delete') and resource ('a classify run') plus the exact scope ('and its stored outputs (classify group)'). This clearly distinguishes it from related deletion tools like delete_extract_run or delete_parse_run.

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?

'Cannot be undone' implies the tool should be used only when permanent deletion is intended, but the description never explicitly contrasts it with alternatives such as cancel_classify_run. The when-to-use vs alternatives is left to inference rather than stated.

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