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

Annotations already carry readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real behavior: it discloses the value/label pairing and the account_customers name fallback, which an agent cannot infer from the schema. It also maps to a concrete REST endpoint for orientation.

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 compact sentences, both front-loaded (purpose and scope first, output shape second). The parenthetical label explanation is dense but earns its place; nothing is padding.

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?

With no output schema, explaining the value/label shape and the fallback to raw id is exactly the missing information an agent needs. Minor incompleteness remains around date conventions and the dimension_key variants, but nothing critical is absent.

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 only 33%, and the description mentions just two of the four accepted dimension forms, omitting 'dimension_key' and 'dimension:<key>'. It adds useful meaning for external_customer_id labels but says nothing about start_date/end_date format, leaving a real coverage gap only partly compensated.

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?

States a specific verb and resource ('List the distinct values seen for a usage dimension') and pins the scope with a date range. It is immediately distinguishable from query_usage, which it explicitly positions itself upstream of.

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?

Gives a clear when-to-use: 'discovering filter values before calling query_usage', which routes the agent to the correct sibling. It stops short of stating when not to use it (e.g. when filter values are already known, just call query_usage).

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