Bulk-resolve street addresses to OneHome URLs + listing_ids

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

Even though annotations already declare readOnlyHint, openWorldHint, and idempotentHint, the description adds substantial context beyond them: output order preservation, per-row error isolation ('one bad address never fails the whole batch'), the two-rung resolution algorithm, the matched_via field, and a concurrency cap of 6. The closing 'Read-only; safe to call repeatedly' merely restates the annotations and does not contradict them.

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?

The description is front-loaded with its core purpose and every sentence carries a distinct fact: batch cap, input/output shapes, ordering, error isolation, resolution ladder, concurrency limit, and defaults. It earns its length, but it is slightly dense with internal jargon (rung names, 'raw-listings pool'), so a small trim would make it crisper.

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, the description correctly takes on the burden of documenting the return shape, spelling out both the resolved row `{resolved: true, url, listing_id, address}` and the failure row `{resolved: false, error, query}`. Combined with 100% parameter coverage and disclosure of ordering, error isolation, concurrency, defaults, and read-only behavior, an agent has everything needed to invoke this 2-param tool correctly.

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%, setting the baseline at 3, but the description goes further by explaining the input object shape `{address, city?, state?, zip?}` and the group_id default to the magic-link session context plus its role in bounding the search-fallback pool. This adds behavioral meaning to group_id that the schema's own description does not convey.

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?

The opening sentence names a specific verb and resource: 'Resolve up to 100 structured addresses to OneHome canonical portal URLs + listing OSK ids in one call.' It explicitly distinguishes itself from sibling onehome_get_by_address by calling out that both walk the same 2-rung ladder and 'cannot diverge,' so an agent can immediately tell the bulk tool apart from the single-address tool.

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 description clearly positions this as the bulk counterpart of onehome_get_by_address, and the schema notes 'for higher counts, batch into multiple calls,' giving a concrete usage rule. However, it never explicitly states when NOT to use this tool or how it differs from other bulk tools like onehome_bulk_get, so it stops just short of full when/when-not guidance.

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