bulk_action

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

Annotations indicate readOnlyHint=false (mutates) and destructiveHint=true. The description adds supported actions (including destructive delete and move), max IDs, and return counts. This adds some behavioral context beyond annotations, but does not explicitly warn about irreversibility of actions like delete.

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: first covers purpose and actions, second gives limitations and output. No filler, every sentence adds essential information. Ideal conciseness.

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 batch tool with no output schema, the description covers purpose, valid actions, limits, and return type (success/failure counts). It lacks details on error handling or partial success, but overall it provides sufficient context for use.

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 100%, so baseline is 3. The description adds value by specifying that UIDs come from list_emails or search_emails, which is helpful context beyond the schema's parameter descriptions. This extra guidance warrants a 4.

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 clearly states it is a batch operation on multiple emails by UID list, listing supported actions (mark_read, mark_unread, flag, unflag, move, delete). This differentiates it from sibling single-email tools like move_email, delete_email, mark_email.

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 key usage constraints (max 100 IDs per call) and mentions required destination for move. It is clear when to use this tool for batch operations, but does not explicitly state when not to use it or reference alternatives beyond the implied batch-vs-single distinction.

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