Dubai Wealth Index

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

The description goes beyond the readOnly/idempotent annotations by explaining that the markdown rendition is identical to what the URL serves, guaranteeing quote consistency. It also discloses an important nontrivial behavior: a retired building reports its retirement with its area rather than silently redirecting. This is exactly the kind of context annotations alone cannot provide.

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?

Every sentence earns its place: the first defines the core operation, the second explains the markdown guarantee, the third gives workflow context and alternatives, and the fourth captures an important edge case. The description is front-loaded and no sentence is wasted.

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 the rich annotations, high schema coverage, and presence of an output schema, the description covers the full calling context: what the tool does, when to use it, what it returns, and a notable edge case. Nothing needed for correct invocation 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?

The input schema already fully documents the single parameter, including that id can be a search hit id, a site path, or a full URL. The description reinforces this meaning by mentioning 'search hit returned' and 'canonical URL,' but it does not add meaning substantially beyond the schema. With 100% schema coverage, the baseline score of 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?

The description specifies the exact action and resource: retrieving a full document by a search-hit id or canonical site URL, and returning it as markdown. The title reinforces the same meaning, and the final sentence adds a distinguishing edge case, making the tool's purpose unmistakable and clearly differentiated from the sibling get_* tools.

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 gives explicit when-to-use guidance: after search when the whole record is needed rather than a single figure, and for pages not covered by typed tools. It lists concrete examples like rankings, off-plan listings, methodology, and prose pages. However, the claim that rankings and methodology are not covered by typed tools sits awkwardly with the sibling tools get_ranking and get_methodology, so the routing guidance is not perfectly reliable.

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 establish this is read-only and idempotent. The description adds non-obvious behavioral detail: unpublishable yields appear last rather than being hidden, and below-publication-gate buildings are included so the set is not mistaken for the whole market. This significantly reduces misinterpretation risk.

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 dense sentences front-load the area scope and pack in the ordering and inclusion caveats without unnecessary repetition. Both sentences earn their place by clarifying output behavior rather than restating the schema.

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 is conceptually rich, covering medians, sorted buildings, and below-gate trades. However, there is no output schema, no return shape is described, and the interaction between 'every building' and the buildingLimit parameter is unaddressed, which could mislead an agent about pagination or truncation.

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 50%, and the description adds some meaning by tying 'medians by bedroom type' to the bedroom parameter and 'One Dubai area' to the area parameter. However, it adds little for the purpose or buildingLimit parameters, and 'every building it publishes' is left unqualified against the default buildingLimit of 50.

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 the exact scope ('One Dubai area'), the resources returned (medians, medians by bedroom type, every published building), and the ordering rule (by gross yield). This clearly distinguishes it from siblings like get_building (single building) and get_city_overview (city-wide).

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 opening 'One Dubai area' and the title 'Every published building in an area' make the intended use clear: an area-level snapshot of published buildings and medians. It does not explicitly name alternatives or exclusion conditions, but the context is strong enough for an agent to select it correctly.

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 establish read-only and idempotent behavior. The description adds meaningful context beyond that: data comes from registered DLD sales and Ejari contracts, not asking prices, and some series exist only conditionally. This gives an agent useful expectations beyond the annotation hints.

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 dense sentences convey scope, contents, data source, and conditionality without filler. The main purpose is front-loaded, and the source clarification 'never asking prices' 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 read-only retrieval tool with no output schema, the description gives a strong picture of what the response contains and where the data originates. Minor omissions like parameter format or behavior when a building has no record are non-critical given the simple input 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 documents purpose and includeMonthly with descriptions, and the tool description reinforces the sale/rent distinction by mentioning both sale prices and rents. However, the required area and building parameters are left unexplained, and the description does not add enough detail to fully compensate for that 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?

The description states a specific verb and resource: getting the full record for one apartment building. It names concrete fields (median sale prices, rents, gross yield, growth, turnover upside, off-plan uplift, short-let curve), which clearly distinguishes it from siblings like get_building_transactions and get_area.

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 intended use is implied clearly: call this when you need the complete aggregated record for one building. However, it never explicitly contrasts it with get_building_transactions or other siblings, nor states when not to use it.

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 mark the tool read-only and idempotent, and the description adds meaningful caveats beyond that: rent rows exist only at building grain and transaction rows are not snapshot-versioned. It also notes these caveats must be repeated when quoting the data, which is valuable non-obvious behavioral context.

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 sentences with no filler. The purpose, use case, and important caveats are all front-loaded and each sentence 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?

The description gives a clear purpose, explicit use case, and critical data caveats even without an output schema. The main gap is the lack of parameter semantics, but overall the definition is well-rounded for a read-only, idempotent transaction lookup 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 description coverage is 0%, and the description does not explain area, building, or windowMonths. The schema patterns and const values provide some intrinsic meaning, but the description adds no parameter-level guidance, so it fails to compensate for the coverage 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?

The description states a specific verb and resource: it returns the individual registered transactions underlying a building's medians. This clearly separates it from sibling tools like get_building or get_ranking, and the title reinforces the purpose.

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 explicitly says when to use the tool: to check whether a median rests on many comparable sales or a few scattered ones. It does not name alternatives or state when not to use it, but the use case is clear enough for an agent to route correctly.

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 establish the tool as read-only, idempotent, and non-destructive, so the description only needs to add behavioral context. It adds useful scope expectations—citywide figures plus medians for every area—and implies a coverage statement. However, it does not disclose output shape, potential empty results, or data freshness, so it does not go far beyond 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 two sentences with no filler. The first sentence front-loads what the tool returns, and the second sentence states practical use cases. 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?

Given no output schema, the description covers the essential return content and usage intent well. It could be slightly more explicit about how the 'purpose' and 'bedroom' parameters shape the citywide vs. area medians, but the fully documented schema compensates for that gap.

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 input schema documents both parameters fully with enums, defaults, and descriptions, including the important caveat that 'all' is a median rather than a sum. The tool description does not add parameter-specific meaning beyond the schema, so with 100% schema coverage the baseline of 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?

The description clearly identifies the resource as a citywide index overview, listing the statistics returned (counts, median yield, price per square foot, rent and growth) and noting it also covers every area. It positions the tool as a precursor to 'drilling in,' which separates it from more granular area or building tools, though it does not name a sibling explicitly.

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 gives two specific use cases: 'pick an area before drilling in' and 'state the index's coverage.' This tells the agent when the tool is appropriate, though it does not explicitly state when not to use it or name alternative tools.

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?

Beyond the readOnly/idempotent annotations, the description discloses critical interpretive caveats: yields are gross, rents are registered rather than asking, and short-let occupancy is an assumption. These prevent the agent from misquoting figures, adding real behavioral context.

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 compact and front-loaded with the core purpose, followed by usage and caveats. Every sentence earns its place, with no filler or 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?

For a simple one-optional-parameter glossary tool, the description fully covers what the tool returns, why it matters, how it should be used, and the key interpretive constraints. Nothing essential 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 description coverage is 100%, so the schema already explains the 'term' parameter and its enum. The description adds no new parameter-level detail, but that is acceptable given the high schema coverage; the baseline of 3 applies.

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 identifies the tool as the source for how figures are defined and computed, covering glossary, provenance, and constants. This distinguishes it sharply from sibling data-lookup tools like get_area or get_building, which return figures rather than explain them.

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 instruction 'Read it before quoting any figure' explicitly states when to use it. While it does not name alternatives or exclusions, the tool's role as a methodology reference makes alternatives largely irrelevant, so the guidance is adequate.

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 and idempotentHint, so the safety profile is covered. The description adds valuable behavior beyond that: it returns the method behind the number, clarifies that rankings below the ten-building floor are generated rather than measured, and warns that rankings should never be presented as exhaustive.

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 compact and front-loaded, with the core scope in the first sentence. Every subsequent sentence adds an operational or interpretive constraint; there is no filler or repetition.

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 read-mostly tool, the description covers the essential semantics: singular result, area scope, ordering basis, validity threshold, and non-exhaustiveness. The absence of an output schema is somewhat mitigated by stating that the method behind the number is returned, though the exact response shape is left unspecified.

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 only 33%, so the description carries the burden, but it does not explain the limit parameter or the semantic differences among the ranking enum values. It only alludes to the citywide-vs-area distinction, which the schema already partly covers with 'Omit for the citywide list.'

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 the resource precisely: one ranking, citywide or for one area, ordered by exactly one published number. The singular framing distinguishes it from sibling list_rankings, and the mention of the underlying method clarifies what this tool returns beyond a bare list.

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 gives clear context for when the tool is appropriate: for a single published ranking with a real underlying number, and only where at least ten buildings qualify. It does not explicitly name list_rankings or list exclusions, but the singular scope and validity floor make the intended use apparent.

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 annotations already declaring the read-only, idempotent, non-destructive profile, the description adds real behavioral context: the Land Department has no per-villa building record, so no per-villa figure is possible, and the response declares which rent grain the yield uses and must be quoted. 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?

Three dense sentences with no filler; the resource and key metrics are front-loaded, followed by the data-availability caveat and the critical quoting instruction.

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?

Despite no output schema, the description lists the returned metrics (median price, rent, gross yield, growth, bedroom breakdown), the grain caveat, and the quote-it requirement, which is largely sufficient. It loses a point because the effect of the purpose parameter on the returned record is not explained and there is no output schema to fill that gap.

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 bare community parameter is compensated by concrete valid examples (Arabian Ranches, The Springs, The Valley) and grain clarification. The purpose parameter is already documented in the schema; however, the description does not explain how purpose changes the response, and the schema's 'A building may publish one...' phrasing is slightly mismatched with the villa-community scope.

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?

Description names a specific resource (a Dubai villa community), gives example communities, and lists the exact metrics returned. The 'community grain only / no per-villa figure' sentence distinguishes it from building-level tools like get_building.

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 makes the applicable grain explicit ('Community grain only') and tells the agent not to expect a per-villa figure, which is a clear when/when-not boundary. It does not name alternative sibling tools or state when to prefer get_area/get_city_overview, so it stops short of full routing guidance.

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 establish read-only, idempotent, and non-destructive behavior. The description adds meaningful behavioral context beyond those annotations: it reports buildings that fell below the publication gate instead of silently dropping them, and it clarifies reliance on the signed-in account.

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 concise sentences, each earning its place: the first states the core behavior, the second explains an important edge case, and the third differentiates the tool from its siblings. The main purpose 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?

For a simple zero-parameter, read-only listing tool, the description covers what is returned, how account scoping works, and what happens to non-publishable saved buildings. No output schema exists, but the return semantics are described sufficiently.

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 there is no parameter semantics for the description to clarify. The description instead adds useful output and scoping context, which is more than needed given the empty 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?

The description clearly states the tool lists buildings saved on the signed-in account along with their current figures. It also distinguishes itself from siblings by noting it is the one tool here that reads account-specific 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?

The description provides clear context: use this tool when account-scoped saved buildings are needed, and it explicitly signals that sibling tools are not account-specific. It stops short of naming alternatives or stating explicit exclusions, but the guidance is sufficient for a zero-parameter tool.

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 establish readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is clear. The description adds content scope and a reading-order caveat but does not disclose additional behavioral traits such as response format, ordering, size, or any rate limit or authentication needs. No contradiction with annotations exists.

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 tightly-packed sentence with no filler or redundancy. It front-loads the tool's resource scope ('Every ranking this index publishes') and compresses both content and usage guidance into one efficient clause.

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 parameters, no output schema, and strong safety annotations, the description only needs to convey what the catalogue contains and how it fits into the workflow. It does so directly by listing the contents and explicitly saying to read this before get_ranking.

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 tool has zero parameters and 100% schema coverage, so there is no parameter surface for the description to clarify. The description still adds meaning by explaining what the empty call returns: every ranking, the method behind each, and the relevant areas.

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 the resource ('every ranking this index publishes') and states exactly what is included: 'the exact method behind each' and 'the areas an area-level version exists for'. It also differentiates from get_ranking by instructing the agent to read it before calling get_ranking.

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 an explicit directive: 'Read it before get_ranking', establishing when this tool should be used in the workflow. It also states the follow-through obligation to 'quote the method alongside any figure taken from a list'. However, it does not explicitly describe when-not-to-use it or name alternative siblings with a conditional 'instead' statement.

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?

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds meaningful behavior: trigram-based fuzzy matching and the publication-gate filter ensuring results always link to existing pages. This gives the agent expectations for recall and result validity.

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 dense sentences with no filler. The first sentence states purpose, the second adds behavioral context, and the third provides workflow guidance. Every clause contributes meaning.

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 is complete for this tool's simplicity: it explains what is searched, how matching behaves, what results guarantee, and how responses should be chained to sibling tools. The annotations cover safety and idempotence, and an output schema exists, so return-value documentation is not required.

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 input schema has 0% description coverage, so the description compensates for the key 'query' parameter by explaining it is a name and that matching tolerates misspellings. The optional 'limit' parameter is not explained in prose, but its schema constraints (default 8, max 20) make it self-explanatory.

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 opens with a specific verb-resource pair: 'Find a building, area or project by name.' It clearly distinguishes this search tool from the sibling fetch/get_building/get_area tools by explaining that search resolves names and then hands off IDs or slugs to those 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?

The description gives explicit routing guidance: 'Call this first when a question names a place', then explains the follow-up steps to fetch or get_building/get_area. This makes it obvious when to use search versus the alternatives.

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