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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered; the description still adds real value on top by promising it 'never returns payment details' and by mapping response sections to their meaning. The instruction to share billing_url instead of attempting plan changes is behavioral guidance an agent could not derive from structured fields.

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?

Purpose and trigger are front-loaded correctly, but the single dense paragraph packs parenthesized field paths (offer.payment_needed, extra_credits.billed_after_use) into prose, which reads like schema restatement rather than guidance. It is information-dense but not well-structured; bullet separation of 'when to call', 'what it returns' and 'what it cannot do' would earn its place better.

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?

An output schema exists, so return values need not be fully specified, yet the description still flags the salient sections an agent must reason about. With zero parameters and full annotation coverage, nothing essential for correct invocation is missing; only the crammed formatting keeps it from being exemplary.

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?

The tool takes no parameters (schema is an empty object with additionalProperties false), so there is nothing for the description to disambiguate. Baseline for a zero-parameter tool is a 4; the description earns the top mark by instead spending its words on what the call returns and when to make it.

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?

Opens with a specific verb and resource ('Check the plan and credits left') and enumerates the credit categories returned (plan credits this month, free trial, purchased). It goes on to name the concrete sub-fields (subscription, offer.payment_needed, extra_credits.billed_after_use), so an agent knows exactly what this returns versus a generic account or usage probe.

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?

States both trigger conditions explicitly: 'before planning paid runs, or after a 402 refusal' – the second is a precise, actionable routing rule. It also draws a hard boundary around what this tool cannot do (changing, cancelling or resuming the plan) and redirects that work to a human on the billing page rather than leaving the agent to try alternatives.

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