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

The description adds useful behavior beyond the annotations: the operation is reversible, it processes up to 200 bookmarks, and it returns only ids whose state actually changed. This complements the idempotentHint heuristic and explains the practical effect of repeated calls.

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 with every clause carrying information: scope, action, reversibility, and return behavior. The most important operational detail—archive or restore up to 200—is front-loaded.

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?

Given the lightweight input schema, output schema presence, and annotations, the description covers the core facts an agent needs: batch limit, reversibility, idempotent-like return behavior, and the two possible states. It does not detail invalid-id or partial-failure handling, but that is beyond the minimum needed for correct invocation.

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 schema already documents the archived boolean and the ids array shape. The description adds 'bookmark' context to ids and the 200-item batch limit, but it does not explain id semantics further or cover edge cases. With only 50% schema description coverage, this is adequate but not thorough.

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?

The description names a specific operation—archive or restore bookmarks—and scopes it by batch size (up to 200). It clearly differentiates this from single-item operations like save_bookmark or update_bookmark through the 'in one call' batch framing.

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 by mentioning 'up to 200 bookmarks in one call' and reversibility, but it does not explicitly say when to choose this over sibling tools or when not to use it. There is no explicit alternative routing like 'for a single bookmark, use update_bookmark.'

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