Zillow MCP — Property Data, Zestimates & Listings for AI Agents

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

No annotations are provided, so the description must convey behavior. It clearly indicates a read operation ('Returns') and specifies the two outputs, but it does not disclose potential edge cases like missing Zestimate data or errors for invalid zpids.

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 a single, concise sentence that front-loads the key purpose and mentions the input and outputs. No wasted words.

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 tool has one parameter and two clear outputs, and the description covers both. As a simple read-only valuation retriever with no output schema, the description adequately covers the essential context.

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 describes zpid as 'Numeric Zillow property id.' The description only adds 'by zpid' which reinforces the parameter's role but does not add new semantic detail beyond the schema. Baseline 3 applies due to full schema coverage.

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 uses 'Returns Zillow's automated valuation (Zestimate) and rent Zestimate' with a specific verb and resource, making it clear this tool retrieves valuation data by zpid. It distinguishes itself from sibling lookup tools which focus on property information.

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 implies usage when a zpid is known and valuation is needed, but it does not explicitly state when to prefer this over the lookup tools or mention any exclusions. No alternative tools are referenced.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It discloses the cost (3 credits) and the return contents, which is useful. However, it does not mention what happens for invalid/non-existent addresses, potential null results, rate limits, or other operational caveats. The transparency is partial.

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 two sentences, front-loaded with the core function ('Returns full Zillow property data...') and includes a useful cost note. Every word is purposeful with no redundancy or fluff.

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 there is no output schema, the description compensates by listing the major data types returned (price, Zestimate, photos, schools, taxes, agent contact, price history) and the cost. It lacks details on error handling or not-found scenarios, but for a simple single-param lookup, this is a fairly complete description.

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 has full coverage of the single parameter 'address' with a detailed description and example. The description adds the 'U.S.' qualifier but little else beyond the schema. Baseline 3 is appropriate since the schema carries the semantic load.

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 returns full Zillow property data for a U.S. address, listing specific data types (price, Zestimate, photos, schools, taxes, agent contact, price history). It distinguishes from siblings like lookup_property_by_zpid (by ID) and get_zestimate (only Zestimate) by focusing on address-based lookup.

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 implies usage when a U.S. address is available, but it does not explicitly compare to alternatives or state when not to use it. The mention of 'Costs 3 credits' is operational, not usage guidance. No clear when/when-not guidance is provided.

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

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

With no annotations, the description carries the burden and adds meaningful behavior: 'Cache-served when fresh (24h)' and 'Costs 1 credit on a cache miss.' This goes beyond a simple definition, though it doesn't cover error handling or return details.

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: the first states the core purpose, the second adds caching and cost details. No filler, information is front-loaded and every word earns its place.

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 simple single-parameter lookup with no output schema, the description adequately explains what it returns and key behavioral nuances (cache, cost). A slight expansion on what 'full property data' includes would improve completeness, but it is largely sufficient.

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 covers the sole parameter zpid 100% with a clear example, so baseline is 3. The description adds no additional parameter-specific meaning beyond confirming it is the lookup key.

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 states 'Returns full property data for a given Zillow property id' with a specific verb and resource, and the 'by_zpid' suffix clearly distinguishes it from lookup_property_by_address, get_zestimate, and search_listings.

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?

Usage is implied (use when you have a zpid), but there is no explicit guidance on when to prefer this over lookup_property_by_address or other siblings, nor when not to use it. No exclusions or alternatives are mentioned.

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

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

No annotations are provided, so the description carries the full burden for behavioral disclosure. It states the filtering capabilities but does not mention pagination, result limits, return format, or any side effects. For a search tool with no output schema, this leaves significant behavioral ambiguity.

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?

A single, well-structured sentence that front-loads the action and resource, then lists the key filters. Every element adds value and there is no 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 tool has no output schema and no annotations, so the description should clarify return behavior. It implies the result is a set of listings but does not mention pagination, result ordering, or what fields are returned. The input parameters are well covered, but the output side is under-specified.

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 schema already documents each parameter. The description adds only minimal clarity by naming the filter categories ('for-sale, for-rent, or sold' and 'bedroom and price-ceiling filters'), which mostly mirrors the schema. This meets the baseline but does not exceed it.

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 uses a specific verb ('Search') and clearly identifies the resource (U.S. property listings) and scope (inside a bounding box). It distinguishes itself from the sibling tools, which are individual property lookups (by address, zpid, or zestimate), by emphasizing geographic area 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 conveys the primary use case: finding listings within a geographic bounding box with optional filters. It does not explicitly state when to avoid this tool or mention alternatives, but the spatial-search context is clear enough to guide selection relative to the individual-property lookup siblings.

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