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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: eligibility is limited to completed runs, and in-flight runs may be rejected. It still doesn't say whether the underlying result artifacts are destroyed or retained.

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 short sentences with zero filler; the action is front-loaded and the eligibility caveat follows immediately. Nothing could be removed without losing information.

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 one-parameter destructive delete with no output schema and full annotation coverage, the description supplies the essential eligibility constraint. The remaining gap is whether deleting a run cascades to related transcripts or artifacts, which an agent might reasonably want to know.

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?

The single `id` parameter is fully documented in the schema (100% coverage) including pattern, length bounds, and provenance ("returned by a previous request"). The description adds nothing about the identifier, so the baseline 3 is appropriate — the schema does all the work.

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 gives a specific verb and resource ("Delete a completed simulation result"), which cleanly separates it from delete_simulation (the config) and from list/get/start_simulation_run siblings. It stops short of naming any sibling explicitly, so the agent must infer the run-vs-simulation distinction from the noun alone.

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?

"Running runs may reject deletion" provides one useful precondition, effectively bounding when the call will succeed. However, it offers no routing guidance — it never says to use delete_simulation for the parent definition or which tool to use to stop an in-flight run before deleting it.

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