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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description adds meaningful context by clarifying that archiving is reversible: clients go to the archive and can be recovered via restore_from_archive. This goes beyond the annotation's blunt 'destructive' flag and prevents the agent from assuming permanent deletion.

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, no filler, with the core action front-loaded and the important reversibility nuance stated immediately after. Every phrase earns its place.

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 single-parameter batch operation with an output schema, destructiveHint, and reversibility info, the description covers everything an agent needs to select and invoke the tool correctly. The recovery references provide the surrounding context that makes the outcome predictable.

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?

The single parameter ids is fully documented in the schema with 'Array of client IDs to archive (from list_clients)', so the description need not repeat it. The description adds only the generic 'by ID' phrase, which is already implied by the schema.

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 ('Archive'), a resource ('clients'), and a clear scope ('several by ID in one call'), distinguishing it from the singular archive_client sibling. The phrase 'not away' clarifies that this is an archive operation, not deletion.

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?

The description implies batch usage ('several clients by ID in one call'), which faintly contrasts with archive_client, but it never explicitly says when to choose one over the other or when not to use it. It also does not mention the relationship to list_archive or restore_from_archive as a lifecycle step.

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