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

Annotations already cover read-only/idempotent safety, so the description adds real context beyond them: default ordering (newest first), the plan gate, and returned fields. Missing pagination/empty-state behavior keeps it short of 5.

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?

Three compact clauses: what it lists and ordering, the returned fields, then the plan gate and the sibling redirect. Front-loaded and waste-free.

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?

A simple zero-required-param read list with a fully documented schema and annotations; the description covers purpose, scope, ordering, plan gate and next step. Pagination behavior is the only notable omission, minor given the limit parameter.

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 rich enum and limit descriptions, so the schema carries parameter meaning. The description adds only the implicit default sort order and the 'one website' scoping already implied by website_id's 'Omit to use primary'.

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?

Specific verb+resource ('List the email conversations') scoped to one website's Email inbox, and it names the returned fields (subject, sender, snippet, needs-answer flag). It is clearly distinguished from siblings like list_conversations, list_tickets and get_email_thread.

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?

Explicitly routes single-thread reads to get_email_thread, and the plan requirement ('Pro plan or higher') plus 'one website' scoping tells the agent prerequisites. No explicit when-not-to-use for e.g. list_conversations vs email, so not a 5.

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