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

Beyond the readOnly/idempotent/no-destructive annotations, the description discloses the result taxonomy (districts_found, none_found, outside_coverage), the critical caveat that none_found is NOT proof no district applies, and the meaning of near_boundary/nearby for parcels straddling a boundary. It further sets handling rules for null figures, tax-rate inference, and notice requirements, which are exactly the behavioral constraints an agent cannot get 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?

Well front-loaded: coverage, then returned fields, then usage routing, then caveats. Most sentences carry real information, but the trailing fragment "Growth plans and up; counts 1 address lookup." is opaque and does not earn its place, slightly diluting an otherwise tight, if dense, paragraph.

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?

With no output schema and no annotation coverage of returns, the description carries the full burden and meets it: it lists every returned attribute (name, type, status, counties, tax rate with report year, outstanding debt, website, notice statute) and all three result statuses. Nothing an agent needs to interpret or safely report the output 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 description coverage is 100% and every parameter (lat, lon, geometry enum, include_inactive) is documented in the schema itself. The description reinforces the point-in-parcel idea for the coordinate pair but never mentions geometry or include_inactive, so it adds no meaning beyond the schema — the baseline 3 for fully covered schemas 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?

Opens with a specific verb and resource ("List the Texas special taxing districts that contain a latitude/longitude") and enumerates exactly which district types are covered (MUD, WCID, fresh water supply, levee, PID) plus the source (TCEQ, city publication). It also names sibling tools (geocode, parcel_lookup) that produce the input, so an agent can distinguish it from a plain geocoder without inspecting schemas.

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 explicit routing: "Geocode an address first (geocode tool) or use a point inside the parcel (parcel_lookup)" — a clear when-to-use and how-to-prepare rule naming both alternatives. It also states the scope limit that PID coverage exists only "where cities publish them" and says coverage appears in the answer, so the agent knows the condition under which results are partial.

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