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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that: the call is free of charge, it reads nothing outside Tanod, and even discloses how the key is located (URL ?key= or Authorization: Bearer header), which is exactly the kind of operational detail an agent needs. It stops short of describing pagination/limits on 'recent purchases', hence 4 not 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?

A single sentence of dense, front-loaded information plus a short clarifier about cost and scope. Every clause carries payload — resource, data returned, key location, cost, and read boundary — with no filler.

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 zero-parameter read tool with no output schema, the description covers what is returned (balance, recent purchases/charges, how to add credit), what it costs, what it trusts, and what it touches. There is no material question left before invoking it.

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?

Zero parameters, so baseline is 4 per the rubric. The description's auth explanation (where the tnd_ key is supplied) further clarifies that no argument is needed to identify the account, which is the semantic gap a no-param tool could otherwise leave.

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 verb+resource: the balance of the prepaid Tanod credit key, plus recent purchases/charges and how to add credit. The domain-qualified 'Tanod credit key' separates it in spirit from generic siblings like get_balance or get_solana_balance, but the description never names those alternatives, so the differentiation is implicit rather than explicit.

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?

'Free; reads nothing outside Tanod' gives useful cost and scope context, and the purpose implies the obvious use case (checking whether you have credit left before calling paid tools). However, there is no explicit when-to-use/when-not statement and no reference to a sibling tool for the alternative case.

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