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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=true), and the description adds substantial behavior: the selection replaces all library rights with EDITOR on exactly those libraries, an empty selection removes them, project rights stay unchanged, a dedicated service account is required, and access is not changed yet. It stops short of explaining what 'prepare' persists, but this is well beyond the annotations.

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?

Six sentences, all front-loaded with purpose before semantics, review instruction, and prerequisites. Each sentence carries useful information; only slight tightening would be possible.

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?

No output schema exists, so the description must carry behavior, and it does: staging semantics, replacement/removal effects, project-rights invariance, service-account prerequisite, and a user-review step. An agent has enough to call it correctly, though what a successful prepare returns is not described.

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 67%: projectId and idempotencyKey are documented in the schema, but collectionIds has no schema description. The description compensates by explaining that the selection replaces rights on exactly those libraries and that an empty selection removes them, giving the array parameter real semantic meaning.

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 ('Prepare') and resource ('business libraries ... for this dossier'), and explicitly differentiates from the apply sibling by noting 'Does not change access yet.' An agent can tell this is the staging step versus helvabase_apply_dossier_library_access without opening either schema.

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 clear context: review the before/after list with the user before applying, and requires a service account dedicated to the dossier. It implies the when-not (not the actual apply) via 'Does not change access yet,' but never names the apply sibling explicitly.

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