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

Annotations already declare destructiveHint=true, but the description goes further: it enumerates exactly what is destroyed, notes the operation is permanent, and discloses the needs_confirmation round-trip and required follow-up behavior. That is real behavioral context beyond the structured hints.

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 tight sentences, front-loaded with the destructive cascade, then the alternative, then the id source and confirmation protocol. Every clause earns its place with no 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 tool with no output schema, the description supplies the cascade scope, reversibility, routing alternative, id provenance, and the needs_confirmation continuation path. An agent has everything required to call it safely.

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%, so studyId, workspace, and approvalId are already documented. The description still adds the provenance of the id (prism_studies_list_workspace) and the role of approvalId in the confirmation flow, which meaningfully complements the schema without re-teaching it.

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 (permanently deletes) and resource (study), plus the exact cascade scope: responses, interviews, analysis, share links. An agent immediately knows this is a destructive, full-cascade delete rather than a soft 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?

Explicitly names when to use it (a draft that won't be fielded, or a duplicate) and when not to, with the alternative sibling and parameter spelled out: 'prefer prism_studies_update closed: true — that keeps the data.' Nothing is left to inference.

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