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

Annotations flag destructive/openWorld, and the description adds crucial detail beyond them: this replaces the entire list, an empty list removes all access, and widening requires user consent. These are exactly the behaviors an agent must know before calling a destructive setter.

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 core action and scope, then the replacement warning, then the consent rule. No padding or restated field names.

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 mutation tool this covers purpose, full-replace semantics, empty-list behavior, id sourcing, and consent. It omits what happens to in-flight runs or whether a prior state can be recovered, a minor 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 coverage is 75% and already documents grants/version/workspace/approvalId; the description adds sourcing guidance (where targetIds and published versions come from) that the schema does not state, which is meaningful beyond the baseline.

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 — setting what an interface may run by granting flows and shims pinned to published versions. The scope phrase 'the interface's ONLY reach into the workspace' pins down exactly what this tool governs, distinct from napkin_interfaces_write/publish siblings.

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 the key when-to-use context (replace the whole grant list, include everything to keep) plus where the required ids/versions come from (workbench_flows_list / workbench_shim_list and revisions), and a caution to ask the user before widening. It does not name a sibling alternative or a when-not-to-use case, keeping it below a 5.

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