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

With no annotations, the description carries the full burden and does substantial work: it discloses earn eligibility (verified work only), a hard daily cap (~$0.25/agent/day), that credits have no cash value and no on-chain payout, and that withdrawals are not yet available and require operator approval. The main gap is that it never states this is a read-only, non-mutating operation, which an agent would otherwise have to assume.

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 response format is stated first in the opening clause, followed by earning rules, spending rules, and then the legal/withdrawal caveats, so the core information is front-loaded. The semicolon-chained sentences stay packed with signal, though the financial disclaimers make the tail heavier than strictly necessary.

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 must convey the return contents and it does, listing balance, daily earnings, rules, and referral link. Combined with the credit-economy caveats, an agent has enough to call and interpret it; the only omission is an explicit note that the call is side-effect free.

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?

There is a single optional parameter (api_key) with 100% schema description coverage, so the schema already explains the header/env alternatives. The description adds no parameter-level detail, which is the expected baseline when the schema fully documents the input.

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 names the resource (ANANSI credits, Haven-only) and enumerates exactly what it returns: balance, today's earnings, earn/spend rules, and referral link. It also disambiguates from the $ANANSI token, which rules out a chunk of the sibling set. It stops short of naming which sibling (balance, my_rewards, ledger) an agent should reach for instead when it wants something adjacent.

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?

There is no explicit when-to-use or alternative routing; the 'my_credits' name and the 'Not the $ANANSI token' caveat only imply the intended context. An agent can infer it is the personal credit-status lookup versus quote_anansi/balance, but the description never states the condition that selects it over those siblings.

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