Look up an NYC tax lot

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

Goes well past the annotations (which only cover readOnly/idempotent/openWorld/destructive): it discloses data provenance (MapPLUTO via NYRezone), the explicit error-instead-of-guess behavior on ambiguous addresses, and a hard data-exclusion guarantee that owner and assessment data are never returned. These are exactly the operational traits an agent cannot infer from structured fields.

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?

Four tight sentences, no filler, with the key constraint (exactly one key) front-loaded before the format rules and the return/exclusion details. Every sentence carries distinct 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?

For a two-parameter read lookup with an output schema, the definition covers identity, inputs, format rules, error behavior, and data boundaries, so an agent can invoke it correctly without further inference.

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 already 100%, so the schema documents both fields; the description still contributes the mutual-exclusivity constraint ('exactly one of address or bbl') that no schema-level oneOf encodes, plus the house-number prefix requirement. It adds real selection semantics beyond the baseline.

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?

Opens with a specific verb+resource ('Look up one NYC tax lot') and immediately scopes it by the two accepted keys (street address OR 10-digit BBL). It also enumerates the returned fields and names the data source, which cleanly separates it from the sibling zoning-district tools that answer a different question.

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 concrete selection rule ('Provide exactly one of address or bbl') plus address formatting requirements and the failure mode for ambiguous/unknown addresses. It stops short of naming an alternative tool for when a lot lookup is the wrong choice, but the usage context is otherwise unambiguous.

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