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

Goes well beyond the readOnly/openWorld annotations: it discloses that computation is deterministic from a production engine rather than estimated, that no third-party data is used, what the result contains (per-bracket breakdown, $5 DOR technology fee, rate-assumption caveats), and an explicit obligation to pass through attributions and the disclaimer. That last point is actionable behavior an agent could not infer from 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?

Front-loaded with the purpose and computation basis, then scope, then output expectations — a sensible order. Slightly dense in the middle, and 'Uses no third-party data' is close to filler given the adjacent attributions sentence, but nothing is truly 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?

An output schema exists, so return values need not be retold, yet the description still flags the salient parts (breakdown, fee, caveats, attributions, disclaimer) that require downstream handling. Combined with the scope limits and determinism claim, an agent has everything needed to call this correctly and use the response.

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 both parameters are already documented, establishing the baseline of 3. The description adds only marginal meaning beyond the schema — the county drives the local rate, and there is a caveat that city-level exceptions may require verifying the DOR location code — but it does not clarify the seller-paid default's interaction with any parameter.

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 — calculate Washington State REET for one sale — with the statutory basis (RCW 82.45) and the exact composition (state graduated brackets plus county local rate). No sibling tool in the list computes excise tax, and the description makes that scope unambiguous.

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 a clear trigger ('Use when you need the exact excise tax owed on a WA home sale') plus a hard scope exclusion ('Washington State counties only') and a default assumption (seller-paid). It does not name an alternative tool for out-of-state or buyer-paid cases, which keeps it 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.