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

Annotations already declare destructiveHint=true, idempotentHint=false and non-read-only, so the safety profile is covered. The description still earns credit by disclosing the dual deletion scope (server + local cache), the preservation of runs, and the blocking condition for running experiments. It stops short of stating irreversibility or what the response contains, but the output schema covers the latter.

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 sentences, each carrying a distinct fact: what is deleted, what is preserved and where to delete it, and the precondition. The destructive scope is front-loaded with zero filler.

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 two-parameter tool with full schema documentation, an output schema, and rich annotations, nothing an agent needs is missing — the target, the side effects, the sibling handoff, and the blocking condition are all present.

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% and the schema itself documents both experiment_id's provenance (from experiment.run) and confirm's requirement to be true. The description adds no parameter-level meaning beyond that, 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?

States a specific verb+resource (delete an experiment record) with scope explicitly spelled out as server plus this machine's local cache. It also distinguishes itself from the neighboring deletion tool by noting that individual runs survive and belong to execution.delete.

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 (a still-running experiment cannot be deleted) and an explicit alternative for the adjacent case (delete runs with execution.delete). An agent can decide between this and execution.delete without further inspection.

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