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

Annotations declare a non-read-only, non-destructive, non-idempotent, closed-world tool, and the description adds substantial context on top: default state (off), that nothing is charged when the Stripe link is issued, that the service is free, that each top-up counts as a normal pack purchase, and the exact error code returned while paused. These are behavioral facts the agent could not infer from the annotations or schema.

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 core behavior is front-loaded in the first sentence and each subsequent sentence carries a distinct rule (status read, card flow, consent, paused state) with no filler. It is dense and slightly run-on with parentheticals, but nothing is redundant.

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 5-parameter mutation tool with no output schema, the description covers the write path, failure mode, and consent requirement well. The remaining gap is the return shape when called with no arguments to check status — what the status report contains is not described.

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 20% (only `new_card` is documented), so the description must compensate, and it largely does: `threshold` is defined as a credits balance trigger, `monthly_max` as a per-month cap on top-ups, and `pack` as the thing bought automatically. `enabled` and the meaning of pack_s/m/l are left implicit, so it falls short of fully closing the 80% gap.

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 states a specific dual verb and resource — 'Shows or changes auto top-up' — and immediately defines the mechanism: balance below `threshold` triggers a `pack` purchase, capped at `monthly_max` per month. This is clearly distinct from siblings like buy_credits (one-off purchase) and get_credit_balance (read-only balance), so an agent can route without opening the schema.

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?

It gives explicit mode selection ('Call without arguments to see the status'), a precondition (a saved card, or `new_card: true` to get a Stripe link), a consent rule ('Ask the person before turning it on'), and a blocked-state case (`available` false returns `auto_topup_paused`). It never names a sibling tool as an alternative, which keeps it just short of a 5.

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