Dubai Data — Dubai real estate statistics

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the response is Markdown with figures, limits and a citation line, sourced from daily-updated Dubai Land Department open data under CC BY 4.0.

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 purpose and id format are front-loaded in the first sentence with no wasted lead-in. The trailing data-licensing sentence is useful context but slightly tangential to the call itself.

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?

With no output schema, the description compensates by naming the return fields (id, title, text, url, metadata) and the response format. For a single-parameter read tool this is essentially complete; only the sibling-routing question remains open.

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 0%, so the description carries the full burden and does so well: it defines the single 'id' as 'type:slug', gives a concrete example, and enumerates the valid type prefixes (project, community, developer, area), effectively supplying the enum the schema lacks.

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 verb ('Fetch the full readable record') and the resources it operates on (project, community, developer, area) by id. It is clear what it does, but it never contrasts itself with the close sibling get_entity, leaving the agent to guess which one to call for entity data.

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 through the id format example ('type:slug', e.g. 'community:dubai-marina') and the note that the text matches the datadubai.ae page, but there is no explicit when-to-use or when-not guidance and no mention of alternatives such as get_entity or search.

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?

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds real behavioral context beyond that: the data origin (Dubai Land Department open data, updated daily, CC BY 4.0), that monthly price history may be truncated, and that each response carries a source URL.

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?

Front-loaded with purpose and required inputs, then the returned fields and provenance. Dense but every clause earns its place; the inline 'type: a | b | c' enumeration slightly interrupts flow but is useful.

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?

No output schema exists, yet the description enumerates the substantive return fields (price and AED/sqft medians, YoY changes, off-plan share, bedroom breakdown, price history, developer projects) plus provenance and truncation caveat. Nothing an agent needs to call or interpret results is missing.

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 0% and there are no enums in the schema, so the description carries the full burden and does it: it defines slug with a concrete example and supplies the four allowed type values, which are absent from the structured fields.

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 verb (get) and resource (full statistics record) and enumerates exactly which entity kinds it covers (project, community, developer, area). An agent can distinguish it from get_market_summary or get_monthly_report without opening any schema.

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 slug definition ('the last part of its page address, e.g. dubai-marina') makes the required input directly actionable and tells the agent which entity scope to pick. It does not explicitly state when to prefer a sibling such as get_market_summary, so the routing is clear but not fully comparative.

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?

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real context: the data source (Dubai Land Department open data), daily refresh cadence, CC BY 4.0 license, and that each response includes the source page URL. It stops short of describing pagination or latency, but the provenance and freshness disclosure is genuinely useful.

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, no filler. The first front-loads exactly what comes back; the second carries provenance, freshness, license, and attribution URL. Every clause 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?

With no output schema, the description carries the job of telling the agent what it will receive, and it enumerates the return fields (sales count, median price, YoY changes, off-plan share, breakdowns, yearly history, monthly series) plus the source URL. For a zero-parameter read tool, nothing an agent needs to call it correctly is missing.

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?

There are zero parameters, so the baseline is 4. The description correctly adds no parameter semantics because there are none to explain; the detail it does give is about output content rather than inputs.

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 verb (Get) and resource (overall Dubai property market summary) and then enumerates the exact metrics returned. It reads as a distinct aggregate-snapshot tool, separable from siblings like get_monthly_report and list_rankings.

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 phrase 'overall Dubai property market summary' implies usage, but the description never says when to pick this over get_monthly_report or list_rankings, nor names any prerequisites or exclusions. Usage is implied rather than stated.

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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond that: the data source (Dubai Land Department open data), daily refresh cadence, CC BY 4.0 licensing, and that each response embeds the source page URL on datadubai.ae.

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?

Three tight lines: purpose and payload first, parameter semantics next, then data provenance. No filler, and the most important information is front-loaded.

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?

There is no output schema, but the description compensates by enumerating the returned fields (key figures, summary facts, top movers, citation string, source URL). Combined with annotation coverage for safety semantics, an agent has everything needed to call and interpret this tool.

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 0%, so the description must carry parameter meaning, and it does: it specifies the 'YYYY-MM' format and the null/omit behavior for the latest report, neither of which appears in the schema. It stops short of specifying valid date ranges or error behavior for malformed months.

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 names a specific verb (get) and resource (monthly Dubai property market report) and enumerates what the report contains (sales, median price, AED/sqft, YoY, top movers, citation string). It is clear what an agent gets back, though it never explicitly distinguishes itself from the sibling get_market_summary.

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?

It gives a concrete usage rule for the single parameter ('omit for the latest report'), which is genuinely helpful. However, there is no guidance on when to prefer this over the closely named sibling get_market_summary, so the routing guidance is only implied.

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?

Annotations already cover read-only, idempotent, non-destructive, closed-world semantics, so the description is free to add operational context — and it does: data provenance (Dubai Land Department open data, updated daily, CC BY 4.0) and the guarantee that every row carries a url plus a source page URL. It does not mention pagination, but the limit constraint is explicit.

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?

Front-loaded with the core purpose, then kind semantics, then limit, then provenance. Dense but every clause carries information; the provenance sentence is slightly long but justified since no output schema exists.

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?

With no output schema, the description compensates by describing row contents (url, and per-kind metrics) and data freshness/licensing. It is nearly complete for a two-parameter listing tool; only pagination/ordering behavior is left implicit.

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 0% and the schema gives no enum for the required 'kind' parameter, so the description must carry the load — and it enumerates all four kind values with their exact meaning and units. It also bounds 'limit' to 1-100, though it omits that the default is 20 (only in the schema).

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 verb ('List') and resource ('rankings') and then defines the four distinct ranking kinds with their metrics (median rent in AED, gross yield %, sales count with median price and AED/sqft). An agent can immediately tell what each invocation returns and that this is not a time-series or per-entity 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 four kind values imply the use cases, but the description never says when to prefer this tool over siblings like get_market_summary or get_monthly_report, nor any prerequisite or exclusion. Usage is only inferable from the kind definitions.

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?

Annotations already declare read-only, idempotent, non-destructive and closed-world behavior. The description adds genuinely new context: the data source (Dubai Land Department open data), daily update cadence, CC BY 4.0 licensing, the source-page url included in responses, and the caveat that url can be null for projects without a page.

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?

Front-loaded with the core query behavior, then type, then return fields, then provenance. The return-field enumeration is slightly long but each item is useful; no sentence is filler.

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?

With no output schema, the description appropriately covers the return shape (id format 'type:slug', title, type, name, slug, url, key figures). Combined with the provenance note, an agent has what it needs; only the limit parameter and pagination/truncation behavior are unaddressed.

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 0%, so the description must carry the load. It fully specifies query semantics (case/accent-insensitive, all words must match, exact > prefix > contains ranking) and supplies the allowed values for type (project | community | developer | area), which the schema does not even encode as an enum. Only limit is left unexplained.

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 verb and resource domain: 'Search Dubai projects, communities, developers and areas by name.' This is clearly distinguishable from siblings like get_entity (lookup by id) and get_market_summary (aggregate stats), so an agent can route correctly without opening the schema.

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 explains how the query matching works and what the type filter does, which implies the usage context, but it never says when to choose search over fetch/get_entity or when a name search is inappropriate. Usage is inferred rather than stated.

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