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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real value by stating that no purchase is ever performed and the agent must relay buy_url, plus signals like `low` and `expires_next` that affect what the user should be told. It doesn't mention auth requirements or how stale the balance is, so it stops short of 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?

Front-loaded with the core verb and the most operationally important content (credits, buy_url) before the parameter note. The parenthetical field list is dense but every item is a return value the agent may need to report; only the explicit argument echo at the end is slightly redundant with the schema.

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?

No output schema exists, so the description carries the return-value burden and does so for credits in detail; the other sections (usage, limits, keys, storage) are named but their field shapes are not, which is a modest gap. For a zero-required-parameter read tool, however, an agent has enough to call it correctly and interpret the most decision-relevant output.

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 nested `query.language` parameter is documented in the schema, but the description adds the intent behind it — it changes the account language when the user requests it — which the schema alone does not frame as an action. It also implies the argument shape ({"query": {"language": ...}}) inline, disambiguating the nested object.

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+resource ("Read the account") and enumerates exactly what comes back: credit balance, usage, limits, keys, storage, language. No sibling tool touches account state, and the description makes the scope unmistakable 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?

Gives an explicit trigger for the only parameter ("Pass language=\"en\" or \"fr\" ... when the user asks") and an explicit behavioral rule for credit purchases ("Kelpo never buys credits by itself: give the user buy_url"). It does not name an alternative or an explicit when-not-to-call, but for a unique account-read tool there is no real alternative.

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