ContextFetch auto-reload

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

Annotations already flag a non-read-only, idempotent, open-world operation; the description goes further by disclosing that real money is spent automatically, that a saved card is required, and that a $500 monthly ceiling applies. It stops short of saying whether omitted fields are preserved or reset on a partial update, which matters for a configuration-mutating tool.

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 tight sentences: the behavior and its trigger come first, prerequisites and the hard limit second. No filler, and the conditional logic is readable at a glance.

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 and full parameter documentation, the description covers the essentials for a billing-related mutation: what happens, what it costs, what credentials are needed, and what cannot be exceeded. Only the response shape and partial-update semantics are absent, which is acceptable but not complete.

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%, so the baseline is 3; the description earns more by explaining the causal relationship between the parameters — threshold triggers the purchase of pack, bounded by monthly_max_usd. The $500 note largely restates the schema maximum.

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 set of actions (turn on, turn off, change) on a specific resource (auto-reload) and explains the mechanism: below a credit threshold the saved card repurchases a pack up to a monthly cap. This is clearly distinct from siblings like contextfetch_balance or contextfetch_search.

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 clear prerequisites (CONTEXTFETCH_API_KEY and a card saved at checkout) and states the operating condition (credits dropping below the threshold). It does not name an alternative path for raising the cap beyond $500, but the in-tool limit is disclosed.

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