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

Annotations cover read-only safety, but the description adds context they do not: error semantics ('missing contract is 404 and a non-ERC-20 422, both uncharged'), pricing and free tier ('$0.01/call via x402 USDC or a card key, first 25 free; failed calls free'), and the non-idempotence rationale ('each call is charged, so repeats are not free'). It also confirms no state change ('reads or computes only'), consistent with readOnlyHint=true rather than contradicting it.

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-loads what the tool returns, then usage, then errors and pricing; sentences are dense but every clause carries information. The pricing/billing tail is lengthy for a read tool and could be trimmed, which keeps it off a 5.

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?

There is no output schema, so the description correctly explains the return values (raw and token units plus unlimited flag). With error codes, billing behaviour, and a routing pointer to the balance tool, an agent has everything needed to call this correctly and interpret failure.

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 per-parameter docs already carry the baseline. The description still adds behaviour the schema does not: token accepts a ticker or 0x contract, and a bad token yields 404 (unknown) or 422 (non-ERC-20) uncharged — useful error semantics for the parameter, though owner/spender get no extra treatment.

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 and resource ('ERC-20 token allowance on Celo: how much a spender may move from an owner's wallet') and explicitly scopes the return shape (raw, token units, unlimited flag). It also names the sibling it is not ('for the owner's balance use celo_token_balance'), so it is distinguishable from the ~100 sibling tools without opening a 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 concrete trigger conditions ('check an approval before a swap or to audit risky open approvals') and an explicit alternative with the selecting condition ('for the owner's balance use celo_token_balance'). Nothing about when to pick this versus a neighbour is left to inference.

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