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

Annotations already cover readOnly/destructive/openWorld, but the description adds real context beyond them: the $0.01/call x402 USDC or card-key billing, the first 25 calls free, failed calls free, and that repeats are charged — which explains the non-obvious idempotentHint=false in economic rather than state terms. Only gap is that it does not detail casing/rounding of the returned units, which is minor.

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 definition and use cases, then error codes, then pricing — a sensible information order where every sentence carries actionable content. Slightly dense with several clauses in one paragraph, and 'reads or computes only and changes nothing' partly restates readOnlyHint=true.

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?

Only 3 required params, no nested objects, no output schema — yet the description still tells the agent what comes back (raw and human-unit allowance, unlimited flag) and what errors to expect. Nothing needed to call this correctly is missing.

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 baseline is 3; the description earns an extra point by adding meaning beyond the schema — the ticker-or-0x-contract duality of 'token' is tied to concrete error outcomes (404 for missing contract, 422 for non-ERC-20), which the schema does not state. It doesn't add anything for 'owner' or 'spender' beyond the schema's own descriptions.

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: reads ERC-20 allowance on Avalanche (owner → spender), and even enumerates the return values (raw amount, token units, unlimited flag). It explicitly names the sibling it is not ('for the owner's balance use avax_token_balance'), so an agent can route between avax_allowance and avax_token_balance without opening either 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 when-to-use cases ('check an approval before a swap', 'audit risky open approvals') plus an explicit exclusion pointing to avax_token_balance. It also documents the failure branches (missing contract = 404, non-ERC-20 = 422) so the agent knows what invalid input looks like.

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