Bulk-resolve street addresses to OneHome URLs + listing_ids

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

Goes well beyond the annotations (readOnly/openWorld/idempotent). Discloses the deadline-bounded behavior, the `pending` status semantics (retry, not 'no listing'), error_kind values, the 2-rung resolution ladder, matched_via surfaced per row, and concurrency capped at 6 in-flight. This is exactly the kind of behavioral detail annotations cannot express.

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 core purpose and limits, but the middle is dense and repetitive: the pending/retry contract is stated twice, the ladder description is verbose, and the final 'Read-only; safe to call repeatedly' partly repeats the readOnly/idempotent annotations. Information-rich but not tight.

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 2-param bulk tool with no output schema, the description covers input shape, ordering, per-row success/failure schema, error taxonomy, deadline behavior, and resolution provenance. Missing only explicit rate-limit figures or size guidance beyond 'up to 100' and pagination across calls, which is minor.

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% and already documents every parameter, so baseline is 3. The description adds meaning beyond the schema by explaining input ordering is preserved, that group_id defaults to the magic-link session context, and the per-row error contract — context the schema alone does not carry.

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?

Specific verb (resolve), resource (structured addresses), scope (up to 100), and output (OneHome URLs + listing OSK ids). Explicitly distinguishes from the single-row sibling `onehome_get_by_address` by noting both walk the same 2-rung ladder via a shared helper, so an agent can tell why bulk vs single exists.

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?

States clearly when to use bulk (batch address resolution, up to 100) and ties it explicitly to the single-address sibling, but never states when NOT to use it (e.g., when a single address is needed, or when group_id must be overridden). No exclusions or prerequisite guidance.

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