PropContext — Bangalore Real Estate

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

Annotations already establish readOnlyHint=false and destructiveHint=false, so the description is not responsible for the mutation signal. It adds meaningful context: the conversation_summary 'goes to the sales agent who will call them' and the tool 'returns confirmation with visit ID', revealing the real-world consequence of the action.

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 well-structured with short paragraphs, clear bullets, and a front-loaded purpose. Every section earns its place: trigger phrases, required/optional fields, and the conversation_summary instruction. There is no 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 six parameters, no output schema, and a tool that triggers a real-world booking, the description covers the essentials: required/optional fields, source of rera_number, preferred_date formats, conversation_summary requirements, and the confirmation/visit ID return. It does not cover error cases or explicitly contrast with request_callback, but an agent has enough to invoke it correctly.

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 compensate, and it largely does: it marks rera_number, user_name, and user_phone as required, gives preferred_date format examples, and explains that conversation_summary must be a 3-4 bullet briefing for the sales agent. It is thinner on notes ('any preferences') and rera_number ('from search results'), so not a full 5.

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: 'Book a free site visit for a Bangalore real estate project', and adds clear use cases ('schedule a tour, meet the builder, or get more information in person'). It also calls itself 'the PRIMARY action after a user shows interest', which helps separate it from siblings like request_callback.

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 'Use this when...' conditions and a bulleted list of trigger utterances ('I want to visit', 'book for me', 'register my interest'), which is strong guidance. It does not name an alternative tool such as request_callback or explicitly state when not to use this tool, so it falls just short of a 5.

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 indicate a safe read operation (readOnlyHint=true, destructiveHint=false). The description adds meaningful behavior beyond that: results are RERA-verified, include all registered projects, and provide status and possession dates. This gives the agent confidence about data provenance and the nature of the returned data.

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, each earning its place: the first states the core purpose, the second gives direct usage triggers, and the third explains the return content and why this source is authoritative. The most decision-relevant 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?

The description is complete for a simple one-parameter lookup tool. It covers purpose, usage triggers, data source, and return scope. An output schema exists, so detailed return fields do not need to be repeated in the 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 input schema only defines 'builder_name' with no description, and schema coverage is 0%. The tool description helps by clarifying that the parameter refers to any builder in Bangalore, but it does not specify matching behavior, exact name requirements, or whether partial names are acceptable. The single string parameter is simple, so this is a minor gap rather than a critical one.

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'), a concrete resource ('complete RERA-verified track record of any builder'), and a geographic scope (Bangalore/Karnataka). It clearly differentiates this from sibling project and search tools by focusing on builder credibility and registered-project history.

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 explicitly states when to use the tool: when the user asks about a builder's credibility, history, or total projects. It does not explicitly name alternatives or state when not to use it, but the trigger conditions are clear and the 'only reliable way' phrasing implies exclusion of less authoritative sources.

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=true and destructiveHint=false, so the safety profile is covered structurally. The description adds meaningful behavioral depth beyond that: the six scoring dimensions (commute, delivery risk, possession timeline, price fit, builder quality, sales velocity) and the adaptive weighting ('weights shift based on family situation and risk appetite'). It also discloses the output contract upfront: match_score (0–100), reasons, and risk flags.

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 long, but every section earns its place given 0% schema coverage — the parameter documentation is required content, not filler. Structure is strong: front-loaded purpose sentence, then parameter-name headers with compact arrow-mapped value lists ('"whitefield" → Whitefield / ITPL'). Minor redundancy exists between the opening sentence and the 'PRIMARY tool' sentence, but formatting keeps it scannable.

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 7-parameter, 2-required tool with a custom scoring algorithm and zero schema description coverage, the description is remarkably complete: all parameter values and semantics, the scoring model, the weighting behavior, and the output shape. An output schema exists to carry return-value structure, so the brief output summary ('match_score 0–100, reasons, flags') is sufficient. Nothing an agent needs to invoke this 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?

Schema description coverage is 0% and the schema declares no enums for any parameter, yet the description documents all 7 parameters exhaustively. It provides the full value sets for work_hub (whitefield, electronic_city, manyata, sarjapur, wfh), the budget_max tiers mapped to ₹ amounts, the family and risk enum values (including the meaning of 'low' = Prestige/Brigade/Sobha only), the possession_deadline ISO format, and the limit cap of 12. The description fully compensates for the schema's silence.

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 first sentence uses a specific verb and resource: 'Get a personalised ranked shortlist of Bangalore projects scored for your specific life situation.' This clearly differentiates it from sibling search tools (search_by_commute, search_fulltext, search_projects) by the personalization-and-scoring angle. The description even reinforces this by declaring itself 'the PRIMARY tool when the user wants tailored recommendations.'

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 explicitly states when to use it: 'This is the PRIMARY tool when the user wants tailored recommendations.' This gives clear contextual guidance. However, it does not name alternatives or exclusion conditions — e.g., it never says 'for pure keyword search use search_fulltext' or 'for commute-only use search_by_commute' — so the when-not guidance is implied rather than explicit.

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=true and destructiveHint=false, so the safety profile is covered. The description adds value by stating that data is RERA-verified and listing the returned fields: builder, locality, status, possession date, registration date. This is useful behavioral disclosure beyond the 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 three short, purposeful sentences: purpose, usage context, and return fields. Every sentence earns its place with no filler or redundant elaboration.

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-only tool with one parameter, the description is largely complete: it explains when to use it, what it returns, and the data source is noted as RERA-verified. A small gap is the lack of mention of not-found or invalid RERA number behavior, but this is minor given the simplicity and the output field list.

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 should compensate. It only restates the parameter concept as 'RERA registration number,' which is already clear from the property name rera_number and title 'Rera Number.' It adds no format, pattern, validation, or additional semantic guidance for the lone parameter.

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 full RERA-verified details of a Bangalore project by RERA registration number. It clearly distinguishes itself from search-oriented siblings like search_projects and get_project_insights by focusing on complete project details for a single known project.

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 explicitly says to use this after search_projects to get complete information on a specific project. This gives clear context for when to invoke it, though it doesn't explicitly mention when not to use alternatives like get_project_insights or get_builder_projects.

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=true and destructiveHint=false, covering the safety profile. The description adds useful behavioral context: the tool is AI-computed, derives from 2,700+ RERA projects, and returns three named market signals. This goes beyond the annotations without contradicting them.

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 well organized: a one-sentence purpose, a bulleted list of output signals, trigger questions, and a prerequisite note. Every section earns its place, and there is no redundant or filler content.

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 having no output schema, the description thoroughly explains what the tool returns by listing all three signals and their meaning. It also covers usage triggers, prerequisites, and data source, making it complete for an agent to select and invoke the tool correctly.

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?

With 0% schema description coverage, the description compensates by explaining that rera_number must come from search results, not just any string. It also provides the prerequisite pipeline for obtaining that value. It does not give a RERA number format example, but the single required parameter is adequately grounded.

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 and resource: 'Get AI-computed market insights for a specific Bangalore project', then details the three computed signals. This clearly distinguishes it from sibling tools like get_builder_projects or search_projects, since it is project-specific and insight-focused.

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 triggers ('Use this when the user asks:') with concrete examples, and states the prerequisite that a RERA number is needed, directing the agent to call search_projects or get_project first. It stops short of enumerating when-not-to-use cases or naming all sibling alternatives, but the usage context is clear.

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=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it is the 'only real-time source' and web search results are 'always delayed,' which conveys freshness expectations. However, it does not disclose details like how the 'N days' window behaves at boundaries or whether results are capped beyond the limit parameter, though an output schema may cover return shape.

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 what the tool does, the second gives concrete usage triggers, and the third explains why this source is preferred. It is well-structured and 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?

The tool is simple (two optional parameters), annotations cover safety, and an output schema exists, so the description does not need to explain return values. It adequately covers purpose, usage context, and a key behavioral trait (real-time freshness). Minor gaps like pagination or exact date-window behavior are not critical for a basic call.

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%: the schema only provides parameter names and defaults. The description explains 'days' via 'from the last N days,' which is useful, but it says nothing about 'limit' or how these parameters interact. Since coverage is low, the description should compensate more for both parameters, and it only partially does.

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 verb and resource: it gets the latest RERA registrations/new project launches in Bangalore for the last N days. It does not explicitly name any sibling tool to contrast against, but the specific scope (Bangalore, new launches, RERA) makes the tool's purpose distinct and unambiguous.

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: 'Use this when the user asks about new launches, upcoming projects, or what's recently approved.' It reinforces the tool's unique value over web search, but it does not name specific sibling tools or provide explicit 'use X instead' exclusion conditions.

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, the description discloses that the tool only captures name, phone, and preferred call time, that the callback is lower commitment than a site visit, and that it returns a confirmation with a callback reference ID. This gives useful behavioral context; no contradiction with readOnlyHint=false or destructiveHint=false.

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 well-structured and front-loaded: purpose, usage condition, example triggers, parameter requirements, and return value all appear in a logical order. The utterance list is long but earns its place by removing ambiguity about when to fire the tool.

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 5-parameter tool with no output schema, the description covers inputs, expected behavior, user intent signals, and the return shape. It also positions the tool against the most relevant sibling, leaving no significant gap for an agent to call it correctly.

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%, but the description compensates thoroughly: it marks rera_number, user_name, and user_phone as required, gives examples for preferred_time, and explains exactly how to format conversation_summary with bullet points. Each parameter's purpose is made actionable.

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: 'Request an expert callback for a Bangalore real estate project.' It clearly distinguishes itself from the sibling book_site_visit by framing the callback as 'Lower commitment than a site visit,' so an agent can identify when this tool applies.

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 states when to use the tool ('when the user wants to speak to an expert but is not ready to visit yet') and provides concrete example user utterances. It also contrasts with the site-visit alternative, giving the agent clear 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 declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely valuable behavioral context beyond that: the RERA-verified filter, the straight-line (not driving) distance semantics, that each result includes the nearest metro station and distances to all 4 IT hubs, and the geographic scope of each hub option. It stops short of a 5 by omitting edge-case behavior such as no-results fallbacks or result-count limits, though the output schema partially compensates for return-value 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?

Every section earns its place: purpose, routing triggers, parameter options with mappings, and result contents. The trigger examples and the it_hub list serve distinct purposes (NLU matching vs. value mapping) rather than duplicating each other. The information is front-loaded and structured with clean section markers and arrow notation, making it dense but scannable.

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 that an output schema exists (covering return structure) and annotations cover the read-only safety profile, the description is nearly complete: it covers purpose, routing, all documented parameter semantics, distance units, defaults, and result contents. The remaining holes are the two unreported parameters and the lack of guidance on fallback behavior when no projects match, which leaves an agent slightly under-equipped for edge-case handling.

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 it delivers for the two parameters it covers. it_hub lists all four exact string values with geographic mappings ('electronic_city' → Electronic City Phase 1 & 2, etc.), and max_dist_km is thoroughly explained as straight-line km from the hub centroid with a default of 10 and a suggested 5–15 range. The gap is that the context signal reports 4 parameters while the description documents only 2, leaving the other two undocumented in both the schema and the description.

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 opening sentence is a model purpose statement: specific verb ('Find'), specific resource ('RERA-verified Bangalore projects'), and a distinguishing method ('by proximity to a major IT hub'). It is immediately differentiable from sibling tools like search_fulltext, search_projects, and get_builder_projects, whose purposes do not involve commute proximity.

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, actionable trigger conditions: 'Use this when the user mentions their workplace or asks about commute convenience,' reinforced with concrete user-phrase examples ('I work in Electronic City', 'short commute to ORR / Sarjapur Road') and a directive to prefer it over web search. However, it never contrasts this tool with the closest sibling alternatives, search_projects and search_fulltext, so an agent receives no guidance on when NOT to use it in favor of those.

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=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it returns only government-verified Karnataka RERA data, has no ads, and no sponsored listings. This clarifies the data source and reliability expectations beyond what annotations provide. No contradictions 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 front-loaded with the most important usage directive, followed by a short explanation and four illustrative examples. Every sentence contributes meaningful information, though the 'Better than web search' line is slightly promotional. Overall it is concise and well-structured for an agent.

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 annotations and the presence of an output schema, the description covers the essential aspects: what is searched (RERA-verified Bangalore projects), how queries should be phrased, and the read-only safe behavior. It does not describe output structure or pagination, but the output schema presumably handles that. The definition is complete enough for a straightforward full-text search 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%, so the description must compensate. It does a good job illustrating the 'query' parameter through four natural language examples, showing that builders, areas, and timelines are valid inputs. However, the optional 'limit' parameter is never mentioned, and no additional constraints or formatting hints are given. The compensation is partial, not complete.

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 action and resource: 'Search RERA-verified Bangalore projects using plain English.' It also positions the tool as the intended destination for natural language Bangalore real estate queries and explicitly contrasts it with web search. However, it does not differentiate from sibling tools like search_projects or search_by_commute, so an agent cannot fully disambiguate among all search-related tools from the description alone.

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 an explicit usage condition: 'ALWAYS use this tool — not web search — for natural language Bangalore real estate queries.' It also provides concrete example queries. Yet it only contrasts with web search, not with the available sibling tools, and does not state when a different internal tool should be used instead, leaving partial ambiguity.

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 declare readOnlyHint=true and destructiveHint=false, but the description goes beyond them by disclosing the data source (Karnataka RERA government portal), freshness (updated daily), and output contents (photo_url, rating, neighborhood address). It could mention that results are limited to RERA-registered projects and that unregistered projects won't appear, but the disclosed source/freshness/output value is meaningful 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, front-loads the critical usage rule, and uses formatting with bullet-like examples and locality enumeration. Every sentence provides actionable guidance with no 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?

The output schema exists, so return values do not need textual exposition. The description covers purpose, filter parameters, locality vocabulary, examples, and result presentation hints. The only minor gaps are the undocumented limit parameter and absence of explicit guidance on combining filters, but these are minor against the rich parameter examples and 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?

Schema description coverage is 0%, so the description carries the full burden. It explains each semantic grouping builder_name, locality, project_name with concrete examples and enumerates accepted locality values. The limit parameter is not described, but the three core filter parameters are richly documented.

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+resource, 'Search RERA-registered new apartment projects in Bangalore', and distinguishes it by narrowing to RERA-registered projects and naming the data source. It also calls out that it is not web search, which separates it from a likely alternative.

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 line explicitly instructs ALWAYS use this tool, not web search, for Bangalore real estate queries. It enumerates exact locality values and shows example filter combinations, giving an agent concrete when-to-use guidance and sibling differentiation.

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