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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, but the description adds context those flags cannot carry: exactly which dependent data is destroyed, that the operation is permanent/irreversible, and that it is scoped to the authenticated customer. That is real added value over the structured signals.

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, zero waste, and the critical blast-radius information is front-loaded. The irreversibility warning lands before the scoping note, which is the right ordering for a destructive tool.

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, no-output-schema tool with full schema coverage, the description covers the essentials: scope of destruction, irreversibility, and tenant boundary. Auth/permission requirements beyond the superadmin note in the schema are not spelled out, which is the only notable gap.

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 all three parameters are documented in the schema, including the confirm safety flag and the superadmin-only customerId. The description's scope sentence loosely touches customerId, but adds no syntax or format detail beyond the schema, 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 (delete) and resource (agent) and enumerates the exact cascade: runs, run insights, prompt insights, prompt metrics. This distinguishes it from the other delete_* siblings (delete_run, delete_user, delete_webhook, delete_optimization) without the agent needing to open their schemas.

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?

Usage is implied rather than stated: the enumerated cascade tells an agent this is the broad option, so an agent wanting to remove only runs should reach for delete_run instead. However, no alternative is named, and there is no statement of prerequisites or when-not-to-use beyond the irreversibility warning.

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