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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds genuinely useful context beyond them: the return payload is JSON rows or CSV text depending on format, and the detail row shape is customer x plan x method x endpoint. It still omits pagination, row limits and any key/permission expectations, which keeps it off a 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?

Two dense sentences with the resource and output formats front-loaded; nothing is wasted. The '(same as /api/export)' aside adds little for an agent but costs only a few tokens.

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?

There is no output schema, yet the description does state the return shapes, which covers the biggest gap. However, for a 5-parameter export tool it leaves the two required parameters (slug, dashboard_key) undefined and says nothing about result size or whether month is mandatory.

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 0%, so the description must carry parameter meaning. It does well on two enum params (view, format) but leaves slug, dashboard_key and month entirely unexplained — 'monthly' hints at month but does not state its format or whether it is required (it is not). With 3 of 5 params undocumented in both places, it cannot score higher.

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 uses a specific verb+resource ('export ... usage rows') and pins the granularity ('monthly', 'billing-ready'). It explains the two shapes via view=detail vs view=customers, so an agent understands what it gets. It does not explicitly differentiate itself from the sibling get_usage, which is the only remaining ambiguity.

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?

Usage is only implied: choosing view=detail vs view=customers and format=csv is described, but the description never says when to call export_usage instead of the sibling get_usage, nor when csv is preferable to json. The '/api/export' reference is an API pointer rather than selection guidance.

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