Compare OneHome listings side-by-side

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint. The description adds concurrency, error isolation per row, default omission of description and summary, and mention of extracted_features in response. This enriches the agent's understanding of behavior beyond the annotations.

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 detailed but well-structured: purpose first, then input details, error handling, output options. It avoids verbosity but includes necessary clarifications. Minor redundancy (repeating that rows carry all facts) could be trimmed, but overall efficient.

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?

Given no output schema, the description covers input methods, error handling, concurrency, default output omissions, and response structure (rows with extracted_features). Missing details on group_id and exact schema of rows/extracted_features, but sufficient for typical use. Could be more complete by explaining group_id.

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 50%: include_summary and include_description have descriptions, but targets and group_id lack descriptions. The description clarifies targets can use listing_id or url (though saved_search_id is omitted) and explains summary/description params' purpose and defaults. group_id remains unexplained, leaving some gap.

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 description clearly states the tool fetches 2+ listings and aligns them side-by-side. It specifies the verb 'fetch', the resource 'listings', and the action 'compare', distinguishing it from single-property or search tools. The mention of input methods (listing_id or url) and output (rows with extracted_features) further clarifies purpose.

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 gives explicit guidance on how to specify targets (listing_id preferred, url as alternative), error handling (per-target errors, no total failure), and optional outputs (include_summary and include_description). It explains when to opt-in for summary. However, it does not explicitly state when not to use this tool vs. alternative siblings like onehome_get_property.

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