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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is lower, and the description still adds meaningful behavior: negative results are reported plainly, a nearby house is never substituted, and covered streets are returned on a miss. It does not disclose matching semantics such as case sensitivity, exact-vs-partial address matching, or ambiguity handling for common surnames.

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?

Two tight sentences, front-loaded with the lookup scope and followed by the return behavior. Every clause carries information an agent needs: accepted inputs, the handoff target, and the miss contract.

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 a single required parameter, the description carries the return contract itself and does so reasonably: a house path for house_history, or an explicit not-covered message plus covered streets. The only softness is what 'path' concretely contains, which the sibling tool's definition presumably resolves.

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% for the single `query` parameter, so the baseline is 3. The description does add real meaning beyond the schema by imposing the '1945 or earlier' constraint on surname queries, which the schema does not state, but it offers no input formatting guidance (quoting, street-type spelling) for the address form.

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 (look up) and a specific resource (a Vancouver address or pre-1945 resident surname) against AddressLore's coverage, and names the downstream tool house_history. It does not explicitly distinguish itself from the sibling `coverage` tool, even though the miss-path mentions returning 'the covered streets', which superficially overlaps with that sibling.

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 clear activation conditions: an address, or a surname from 1945 or earlier, and routes the agent onward to house_history once a match is found. It stops short of saying when to call `coverage` instead of this tool, so the boundary with that sibling is left to inference.

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