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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds valuable behavioral context: deletion is permanent, stored outputs are included in the deletion scope, and llmContext guidance should be followed. This goes beyond the annotations 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?

Three short, purposeful sentences: the first states the action and object, the second the key irreversible consequence, and the third an operational instruction. There is no filler or redundant restating of the title or annotations.

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 simple destructive tool with a rich input schema and an output schema, the description covers all essential behavioral caveats: permanence, scope of deletion, and the llmContext instruction. The output schema handles return-value expectations, so nothing critical is missing for correct 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 100%, with all three parameters documented in detail, including the environment enum and granted workspace constraints. The description itself offers only minimal parameter-related context, but the schema carries the burden, so the baseline 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 uses a specific verb and resource: it 'permanently delete[s] an edit run and its stored outputs (edit group)'. This clearly distinguishes it from the many delete_* siblings that target other run types, such as delete_classify_run or delete_extract_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?

The description clearly establishes the use case: deleting an edit run. It also provides a caution ('Cannot be undone') that helps an agent confirm destructive intent. It does not explicitly name alternatives, but the sibling set shows no overlapping edit-run deletion tool, so the usage context is effectively unambiguous.

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