save_searchSave the current search as a named alert. The user will receive email digests when new matching listings appear. Requires authentication.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | A human-readable name for the saved search. If omitted, a name is derived from the filters. | |
| query | No | The free-text query string, if any. | |
| filters | No | The structured filter map to persist (same shape as search_listings filters). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses key behaviors: it saves a search, triggers email digests, and requires authentication. It does not mention potential side effects like duplicate handling or mutability, but coverage is strong given the lack of 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 concise (three sentences) and front-loaded with the core purpose. Every sentence adds value without redundancy.
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?
The description covers the main purpose and auth requirement but does not explain return values (e.g., no output schema). For a tool with three optional parameters, it is adequate but not fully complete.
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%, so the parameters are already well-documented in the schema. The description adds no additional meaning beyond what the schema provides, warranting a baseline score of 3.
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 action ('Save the current search'), the resource ('search'), and the outcome ('as a named alert' with email digests). It distinguishes from siblings like list_my_saved_searches and delete_saved_search.
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 includes a prerequisite ('Requires authentication') but does not specify when to use this over alternatives like search_listings or list_my_saved_searches. Usage context is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: listing CRUD, attachment upload workflow, search with interpret, geocoding, saved searches, and registry retrieval. No two tools overlap significantly; even the upload-related tools (sign, confirm, attach) are sequential and distinct.
All tools follow a consistent verb_noun pattern in snake_case (e.g., create_listing, get_registry, search_listings). The naming is predictable and clear, with no mixing of conventions.
With 15 tools, the server covers the core functionalities of a commercial real estate listing system without being bloated. Each tool serves a necessary role, and the count feels well-scoped for the domain.
The tool set is missing critical lifecycle operations: there is no way to delete or archive a listing, nor any tool to publish/unpublish a listing. This leaves an obvious gap in the basic CRUD workflow, which will cause agent failures when users need to remove or finalize listings.