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

Annotations already establish readOnly/destructive/idempotent, and the description adds real behavioral context on top: the call is a free/no-credit-cost read, the balance is shared across all keys, MCP, REST and Archive, the period end is not a guaranteed renewal, receipts are not conversations or full question costs, and the current call is recorded only after preparation. These are non-obvious operational facts an agent cannot derive from the annotations.

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 most important element, the when-to-use trigger, is front-loaded in sentence one, and the remaining sentences each convey distinct facts (sharing, renewal, receipts). The field-enumeration sentence is a dense run-on that is harder to parse than necessary, but nothing is wasted.

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, the description compensates by enumerating the returned keys (credits.limits, transport_limits, allowance, used/pending/remaining, receipts) plus two important caveats about renewal and receipt meaning. It stops short of a clear return structure, but it is strong for a read-only tool whose safety profile is already in the annotations.

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 description coverage is 100%, with limit and cursor both fully documented in the schema (paging, cursor reuse, unchanged query args). The description only alludes to "paged receipts" without adding format or semantics beyond the schema. Baseline 3 is appropriate when the schema already carries the parameter burden.

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 first sentence names a concrete verb (checking) and resource (research-credit balance, spending, research budget), so the tool's job is immediately legible. No sibling tool deals with credits, usage, or receipts, so it is cleanly differentiated from the surrounding catalog. An agent can pick it 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?

"Use when checking research-credit balance, spending or a requested research budget" gives explicit triggering conditions rather than vague implied usage. There are no competing credit-related siblings to disambiguate against, so no exclusion clause is needed. Missing only a when-not case, which is minor here.

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