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

Annotations include destructiveHint: true and readOnlyHint: false, so the description's clarification that the record 'goes to the archive, not away' and can be restored adds valuable context beyond the annotations. It discloses that the operation is reversible and not a permanent deletion, which is critical behavioral information an agent needs. No contradiction with the annotations, as 'destructive' here means a state-changing move, not irreversible destruction.

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?

The description is a concise two-sentence structure. The first sentence states the action and target, the second clarifies the effect and provides the related tools. Every word earns its place, with no fluff or repetition. It is front-loaded with the core purpose and uses the em-dash effectively to add crucial nuance.

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 tool with a single parameter, an output schema present, and annotations covering safety, the description is quite complete. It covers the purpose, the reversible nature, and the related tools (list_archive, restore_from_archive). It does not mention error conditions or prerequisites, but the schema's reference to list_exports implies the ID source. Overall, an agent has enough information to invoke it correctly without ambiguity.

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 input schema already fully describes the single parameter 'id' with the note 'Export ID (from list_exports)', giving 100% coverage. The description adds only the redundant phrase 'by ID' and does not provide any additional semantic details such as format, validity, or constraints. Since the schema carries the full burden, the description's contribution is minimal, warranting the baseline score of 3.

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?

Description states a specific verb ('Archive'), a resource ('a PDF export record'), and the method ('by ID'). It also clarifies the action is not permanent deletion ('not away'), which distinguishes it from destructive delete operations and aligns with the archive_* family of siblings. The mention of list_archive and restore_from_archive further disambiguates its role in the lifecycle.

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 provides lifecycle context by naming list_archive and restore_from_archive, implicitly telling the agent that archiving is reversible and that these tools are the complementary operations. However, it does not explicitly state when to use this tool versus alternatives like delete or other archive tools, though the name and specificity to PDF exports largely remove ambiguity. The 'not away' phrasing also implies it should not be used when permanent deletion is intended.

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