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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds substantial extra context: cost ($0.02 USDC per call via x402), the billing rule that invalid input (400) and 4xx/5xx failures are not settled, the full row shape returned, and the disclaimer that gains need cost basis. This is well beyond what the annotations convey.

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 the user questions and then the required inputs and return contents, so an agent gets the gist immediately. It is dense and slightly long, with some repetition around the tax-advice caveat and CSV output, but nearly every sentence carries usable information.

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 must describe return values, and it does so thoroughly: per-transfer labels, CPA treatment categories, counterparty, tx link, stablecoin USD value, per-asset totals, counts, and optional CSV. Combined with schema-complete parameters, an agent has everything needed to call and interpret 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?

Schema description coverage is 100%, so the schema already documents wallet, chain, year, from, to, include_csv, and via. The description reinforces the base default and the year-vs-from/to alternation but adds no format, constraint, or edge-case meaning beyond the schema, so baseline 3 applies.

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 (crypto transactions for a wallet in a tax year) and frames it around three concrete user questions. An agent can distinguish it from siblings like wallet_risk_check or token_risk_check because it is clearly the tax/ledger reporting tool, not a risk assessment.

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?

The opening example questions make the intended use cases explicit (period activity, accountant export, taxable transfer identification), and the 'record for preparing taxes, not tax advice' caveat sets a scope boundary. It never explicitly names an alternative sibling or says when not to use it, so it stops short of a 5.

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