upload_listing_imageUpload a listing image by URL. Fetches the image, optimizes it, and returns hosted Tu Lugar image URLs to pass into create_listing.images[] or edit_listing.images[]. Rejected if the image fails property-photo moderation.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public https URL of the source image |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide readOnlyHint=false and destructiveHint=false, but description adds that it fetches, optimizes, and applies moderation, which explains its non-read-only behavior. No contradiction.
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?
Two sentences: first states the action and return value, second states a rejection condition. Every sentence adds value, no fluff. Front-loaded with the primary purpose.
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 single-param tool with no output schema, the description covers purpose, integration points, and failure condition. It lacks explicit output format details but the context implies it returns URLs.
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% for the single 'url' parameter. Description does not add any additional semantics beyond what the schema already provides ('Public https URL of the source image'). Baseline 3 is appropriate.
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?
Clear verb 'upload' with specific resource 'listing image'. Description explicitly distinguishes from siblings by stating the output goes to create_listing/edit_listing, which are listed as siblings. The fetch/optimize/moderation flow is well-articulated.
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 the image is rejected if it fails moderation, providing a condition for excluding its use. Mentions passing URLs to specific tools (create_listing, edit_listing). However, no explicit alternative or when-not-to-use beyond moderation failure.
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.
Most tools have distinct purposes covering account management, listings, search, financials, etc. However, `fetch` and `get_listing` both retrieve full listing details, creating potential confusion. Also, `search` and `search_listings` overlap but are differentiated by free-text vs. filtered search.
All tool names follow a consistent `verb_noun` pattern in snake_case (e.g., `create_listing`, `publish_listing`, `connect_account`). The naming is predictable and clear throughout.
At 39 tools, the server is quite large for a real estate domain. While it covers many aspects, some tools like `fetch` and `get_listing` are redundant. The count feels excessive and could be streamlined to around 25-30 without losing functionality.
The tool set covers listing CRUD, various search types, agent/company profiles, financial calculators, inquiries, saved searches, and account management. Minor gaps exist, such as lack of bulk operations or advanced analytics, but core workflows are well-supported.