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 real information beyond them: what is cascaded (events, rows, share link) and that the effect is irreversible. It does not say whether the share link revocation affects existing recipients or whether any permissions or ownership checks apply, which keeps it from a 5.

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 sentences, the destructive scope is front-loaded, and the warning constraint follows immediately. No filler, redundant restatement of the title, or hedging language.

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?

An output schema exists, so return values need not be explained, and the description covers what is destroyed and the confirmation requirement — the essentials for a one-parameter destructive tool. It could be more complete by clarifying whether related artifacts (e.g., paper runs derived from the run) are also affected.

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% and the run_id field already documents provenance ("from list_runs or save_run"), so the schema carries the load. The description adds no syntax, format, or validation detail about run_id, matching the baseline 3 for high-coverage schemas.

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?

States a specific verb and resource ("Permanently delete one of the caller's saved runs") plus the cascade scope ("with its events and rows, and its share link"). The ownership qualifier ("the caller's") and the word "runs" clearly separate it from paper-trading siblings like close_paper_run or archive_paper_strategy without needing to name them.

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?

Gives an explicit precondition — "confirm with the user before calling" — which is the key usage gate for a destructive operation. It stops short of naming alternatives (e.g., that closing a paper run or archiving is a different, non-destructive path), so the agent must infer when deletion is preferable to the sibling tools.

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