check_new_matchesPoll a subscription for listings that appeared since the last check. Call it on a recurring schedule (daily is a good default) with the subscription_token from subscribe_to_search. / Само НОВИТЕ съвпадения по абонамент.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | ISO date/time of the previous check (optional — default: last 7 days) | |
| search_id | Yes | ||
| subscription_token | Yes | Token returned by subscribe_to_search |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only and idempotent behavior, so the description only needs to add contextual detail. It does so by explaining the incremental nature of results and the default 7-day window for the since parameter. No contradiction with 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 and front-loaded with the core action and usage cadence. The Bulgarian sentence repeats the 'only new matches' idea, adding minor redundancy but not harming clarity.
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?
Covers the essential invocation context: polling schedule, token source, and incremental results. Missing explanation of the required search_id and any indication of what the response contains makes it slightly incomplete for a 3-parameter tool with no output schema.
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?
The schema already documents subscription_token and since, and the description reinforces the token's origin and the polling window. However, the required search_id parameter is undocumented in both the schema and the description, leaving a meaningful 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?
States a specific action: poll a subscription for listings that appeared since the last check. The 'only new matches' emphasis and the reference to subscription_token from subscribe_to_search clearly distinguish it from search and subscription-creation siblings.
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?
Explicitly recommends a recurring schedule with daily as the default, and tells the agent where the subscription_token comes from. It does not explicitly name alternative tools or state when not to use this tool, so it stops short of a full 5.
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 targets a distinct action: searching, viewing details, stats, locations, subscription polling/creation, and inquiries. check_new_matches and search_properties both return listings, but one is explicitly subscription-scoped, so there is no real ambiguity.
All tool names follow a consistent lower_snake_case verb-first pattern: check_, get_, list_, search_, send_, subscribe_to_. The style is predictable and easy to follow.
Seven tools is well-scoped for a real estate search and contact server. Each tool covers a distinct step in the user journey without redundancy.
The core workflow is covered: browse locations, search, view details, get price stats, contact the agency, and set/receive new-listing alerts. A minor gap is subscription management, such as unsubscribing or updating a saved search, but agents can work around it.