categorize_inbox_emails

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

Annotations already mark the tool as idempotent and non-destructive. The description adds the key behavioral trait that it consumes AI credits, which goes beyond annotations and helps the agent understand side effects. No contradiction with 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?

The description is a single, efficient sentence that front-loads the purpose and adds a relevant cost warning. No wasted words or redundant information.

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 simple one-parameter tool with no output schema, the description is fairly complete: it states purpose, scope, and cost. It does not explicitly explain the return format, but the phrase 'label intent and priority' suggests the outcome. Given low complexity and good annotations, this is sufficient.

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% with `email_ids` described as 'Email IDs to categorise (max 50 per call)'. The description's mention of 'batch' and 'triaged' adds slight context but does not significantly improve parameter understanding beyond the schema. Baseline 3 is appropriate.

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 a specific verb+resource: 'Run AI categorisation over a batch of inbox emails to label intent and priority.' It distinguishes itself from sibling email tools (send, archive, reply) by focusing on AI triage and labeling. The scope is unambiguous.

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 gives clear usage context: 'Consumes AI credits — pass only the emails you actually need triaged.' This tells the agent when to use the tool (for triage) and provides a cost-based caution, though it does not explicitly name alternatives or exclusion criteria.

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