Small Business Intelligence by Brick & Mortar

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds meaningful behavioral context: multiples must be researched fresh and date-stamped, never hardcoded, and the seller-question list is built from gaps the research surfaces. This goes beyond the structured 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 front-loaded with a precise definition, followed by detailed component breakdown and then example invocations. It is somewhat long but every section contributes value, and the examples clarify abstract concepts. It earns its length without being bloated.

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 tool with an output schema, the description need not explain return values, and it provides a thorough account of purpose, inputs through examples, and internal methodology. It gives an agent everything necessary to decide when and how to invoke it, including the types of information to gather before calling.

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 covers all four parameters with descriptions, giving 100% schema_description_coverage. The description reinforces the role of category (determines multiple range) and asking_price (used for sanity-checking), but these add little beyond what the schema provides. Baseline of 3 is appropriate given the strong 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 clearly states the tool produces a pre-diligence framework for brokers or buyers, enumerating specific components (SDE framing, category multiple range, red-flag checklist, seller questions). Example invocations ground the purpose in concrete user needs, making it easy to distinguish from vague or tautological definitions. Though it doesn't explicitly differentiate from siblings, the unique combination of elements makes the function unmistakable.

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?

Example invocations explicitly demonstrate when to use the tool: preparing for diligence on a new target, generating seller questions, checking red flags, and sanity-checking asking prices against multiples. This provides clear context, but there are no explicit 'when not to use' statements or direct comparisons to sibling tools like pricing_benchmark or market_opportunity_scan.

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 carry readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value by disclosing the tool's scope ('digital presence, review signal, competitive position, pricing posture, visibility gaps') and that recommendations are 'evidence-cited', which goes beyond the annotations. No contradictions; the description is consistent with the read-only nature.

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 short paragraphs: the first front-loads the purpose and key features in a single sentence, the second provides three succinct, relevant examples. No filler or repetition; every 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?

Given the tool's complexity (multi-aspect teardown) and that it has an output schema, the description sufficiently explains what it does and the kind of output (structured, evidence-cited recommendations). It could mention potential prerequisites or limitations (e.g., only small businesses, need for accessible data), but the 'flagship' framing and examples give enough guidance 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 100% and each parameter is already well-described (e.g., business_name 'as it appears on its own signage/website', city_metro 'narrows the trade area and comp set', category with guidance on guessing). The description's examples reinforce usage but do not add new semantic detail beyond the schema. Baseline 3 applies because the schema carries the param meaning.

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 function ('full structured teardown of ONE named small business') and lists the concrete aspects it covers (digital presence, review signal, competitive position, pricing posture, visibility gaps, recommendations). It also declares itself 'the flagship tool — start here' which clearly distinguishes it from lower-level siblings like competitor_landscape or pricing_benchmark.

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 clear directive ('start here for any single-business question') and three example invocations that illustrate reasonable scenarios (evaluating a business, diagnosing problems, pre-purchase diligence). It stops short of explicitly naming alternatives or stating when NOT to use it, but the flagship positioning implies it's the entry point, so an agent can infer when to pick it over others.

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 and destructiveHint=false, and the description adds meaningful behavioral context: it explains the tool separates true competitors from adjacent players and produces a positioning matrix plus saturation signals. No contradiction 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 tight and front-loaded: one substantive sentence defines the tool, followed by three representative invocations. Every part serves a purpose, and there is no wasteful repetition of annotation or schema information.

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 mapping tool, the description covers the required category and metro inputs, shows optional radius-style queries, and an output schema exists to describe returns. An agent has enough context to select and invoke this 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?

Schema description coverage is 100%, so the schema already documents all three parameters. The description reinforces the category + metro framing and hints at radius/neighborhood handling through examples, but it does not add essential semantic detail beyond 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?

The description opens with a specific verb and resource: 'Maps the local competitive set for a category + metro.' It then enumerates concrete outputs — true vs. adjacent competitors, a positioning matrix, and saturation signals — making it easy to distinguish from siblings like market_opportunity_scan or pricing_benchmark.

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 examples provide clear usage context by showing real questions this tool answers, such as mapping competitive landscapes or measuring saturation. It does not explicitly name alternative tools or state when not to use it, 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 specify readOnlyHint=true and destructiveHint=false, so the tool is non-destructive. The description adds that it does not re-research but assembles existing outputs, which clarifies behavior beyond annotations. No contradiction 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 concise, using two sentences plus two examples. It front-loads the purpose and lists key aspects (section order, executive-summary rules, etc.) without unnecessary detail. The structure is effective and easy to parse.

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, combined with the input schema (which includes parameter descriptions and an output schema reference), provides sufficient context. Examples illustrate typical use cases, and the 'not re-researched' note clarifies the input handling. No gaps that would prevent correct usage.

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 descriptions for all three parameters, including a detailed explanation for completed_analyses. The tool description itself does not add further parameter semantics, but the schema provides sufficient meaning, so a neutral score 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 states the tool's purpose: assembling outputs of prior tool calls into a client-ready report. It specifies the resource (outputs of prior tool calls) and the verb (assemble), making it distinct from other tools. The examples further clarify the intended use.

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 it assembles outputs from prior tool calls and includes example invocations that show when to use it (after running other tools). The input schema also notes 'not re-researched', reinforcing the condition. This provides clear guidance on when to use the tool versus alternatives.

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 safety is covered. The description adds behavioral context by specifying that the output is a research plan rather than actual data, and by noting limitations ('what the public record cannot answer at all'), which helps set expectations.

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 core purpose and usage guidance are front-loaded in the first two sentences, and the example invocations are genuinely illustrative. It is longer than minimal, but each component adds value for an agent deciding whether and how to call it.

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 an output schema present and 100% parameter coverage, the description does not need to restate return structure. It provides enough context: what the tool does, when to use it, what to pass, and realistic examples. No critical information is missing for correct invocation.

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 parameters are well documented in the schema itself. The description reinforces the intended usage with concrete example questions and places, but it does not add substantial meaning beyond what the schema already provides.

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 ('returns') and resource ('source-first RESEARCH PLAN'), and clarifies the plan's contents: which public record settles the question, how to reach it, what the answer is worth, and what it cannot answer. This clearly distinguishes it from sibling data-retrieval tools like twin_cities_records or market_opportunity_scan.

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 tool BEFORE researching a local market and explains why it matters. It gives multiple example invocations that illustrate appropriate inputs, but it does not explicitly name sibling tools or state when to use them instead.

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, and the description adds useful behavior beyond that: it returns a 'scored checklist' and specifies 'what to check, and in what order'. This goes beyond the structured annotations and helps set output expectations.

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 core sentence is front-loaded and information-dense, followed by three useful example invocations. There is no filler or redundancy, though the example block makes it slightly longer than strictly necessary. Each line 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 audit tool, the description covers the purpose, the facets involved, the output format, and realistic user intents. With an output schema present and annotations covering side-effect safety, nothing critical is missing for an agent 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 100%, so each parameter is already documented in the schema. The tool description itself adds no new parameter-level semantics, only examples; per the rubric, baseline 3 is appropriate when the schema carries the explanatory 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 opens with a specific verb and resource: 'Audits a business's local search presence' and enumerates concrete facets (map-pack factors, listing consistency, category selection, site fundamentals). It is clear and substantive, but it does not explicitly differentiate itself from siblings like business_teardown or competitor_landscape, so it stops short of a 5.

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?

Three example invocations provide clear, concrete triggering contexts, such as 'Why doesn't X show up when someone searches...' and 'Give me a scored GBP/NAP checklist...'. This gives the agent a strong sense of when to call the tool. However, it does not explicitly state when not to use it or name alternative tools for other situations.

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 no contradiction exists. The description adds meaningful behavioral context by stating the analysis uses 'only public signals' and describing the nature of the output (underserved demand, oversaturation, whitespace), which is useful beyond the annotation fields.

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 a single dense purpose sentence followed by compact, varied examples. There is no filler or repetition, and every sentence contributes to understanding what the tool does and how to invoke it.

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 full input schema, readOnly annotations, and presence of an output schema, the description covers the essential decision context, example usage, and analytical scope. Nothing critical is missing 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?

Schema description coverage is 100%, so the baseline is 3. The description adds value by framing the inputs as 'category x metro' and providing three concrete example invocations that demonstrate how to populate category and city_metro with realistic values.

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 ('detects') and resource ('category x metro') and clearly defines the tool's focus: underserved demand, oversaturation, and whitespace. The three example invocations make the purpose concrete and help distinguish it from sibling tools like competitor_landscape or pricing_benchmark.

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 context for when to use the tool ('for someone deciding whether/where to open, expand, or invest') and shows realistic user queries. It does not explicitly name alternatives or exclusion conditions, but the use case is clear enough that an agent can choose it appropriately.

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, non-destructive behavior. The description adds meaningful methodological context: normalization across service bundles and handling of competitors that don't publish prices. No contradictions with annotations; it would benefit from stating data sources or freshness, but the added detail is valuable.

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 core purpose is front-loaded in one strong sentence, and the example invocations support real-world usage. Three examples are slightly repetitive, but each adds a different angle, so the length is justified and not bloated.

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 an output schema present, return values need no elaboration. All three parameters are documented and illustrated, and the description covers key edge behavior around bundled services and unavailable prices. It is complete enough 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?

Schema coverage is 100%, so baseline is 3. The description adds value by showing natural-language mappings for category and city_metro, and by clarifying that services is optional and that a comparable bundle is derived when omitted.

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 names a specific verb and resource: 'Builds a defensible local pricing comparison within a category.' Examples make the category and market scope concrete, and the emphasis on pricing clearly separates it from broader siblings like competitor_landscape or market_opportunity_scan.

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 examples provide clear context for when the tool applies, including benchmarking, checking specific pricing, and handling missing public prices. It does not explicitly name alternatives or say when not to use it, but the pricing-specific framing gives strong enough guidance for selection among siblings.

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?

The description discloses key behaviors beyond annotations: the request goes to a real inbox, is free, requires no account, and must not be reported as sent unless the response status is 'filed'. It also warns against paraphrasing the user's words and against approximating email addresses. These are material side effects and constraints the agent must know, and they complement the non-read-only, open-world annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, then flows logically into usage criteria, pre-call behavior, parameter handling, and post-call reporting. The example invocations are compact and illustrative. Every sentence earns its place; there is no filler or redundant restating of the title.

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 tool with five optional parameters and a nuanced interaction protocol, the description covers everything an agent needs: what the tool does, when to use it, what to ask the user, how to fill each parameter, how to report the result, and example prompts. The existence of an output schema covers return-value details, so nothing critical 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?

Although schema coverage is 100%, the description adds crucial semantics: 'request' must be verbatim, 'context' is the agent's own summary, 'reply_email' must never be guessed, and 'subject' can be a city, sector, dataset, or tool name. It even explains how to elicit missing information from the user before calling. This is far more meaningful than the bare schema descriptions.

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 states a specific action: 'Sends a feature request, a data request or a correction straight to the person who builds this server'. It clearly identifies the tool as a feedback/request channel, which is distinct from the sibling analysis tools. The description also names concrete triggers ('a question it cannot answer, a dataset or column it does not hold'), making its purpose 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 explicitly says 'Use it whenever this server falls short of what the user actually wanted' and enumerates four specific scenarios. It also instructs the agent on when to offer filing a request ('Reaching a wall is not the end of the turn') and what to ask before calling. This is direct, actionable guidance for selecting the tool at runtime.

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?

The description aligns with the readOnlyHint and destructiveHint annotations, indicating a non-mutating analysis operation. It does not explicitly state that no data is modified, but the wording 'mines' and the focus on extracting signal imply a read-only behavior. It adds no extra transparency beyond the annotation but is consistent with it.

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 efficiently enumerates the key analytical outputs without extraneous detail. It is well-structured and immediately communicates the tool's value proposition.

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 covers the core functionality and output types but does not elaborate on the input requirements or output format. Given that an output schema exists and parameter descriptions are complete, the description is sufficiently complete for an agent to understand what the tool does, though it could briefly mention how the location disambiguates businesses.

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 description does not explicitly connect the parameters (business_name, city_metro, category) to the analysis process. While the schema provides individual parameter descriptions, the tool description adds minimal contextual meaning about how these inputs are used to locate and focus the review mining. However, the parameter descriptions are clear enough on their own.

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 mines public reviews and lists specific analytical outputs (complaint taxonomy, theme extraction, sentiment trajectory, differentiators, red flags). It uses a specific verb ('mines') and identifies the resource ('public reviews'), making the purpose unambiguous and distinct from generic search or retrieval 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 implies usage for review analysis but does not explicitly state when to prefer it over alternatives like competitor_landscape or local_visibility_audit. It lacks explicit when-to-use or when-not-to-use guidance, leaving the agent to infer applicability from the listed outputs.

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 and non-destructive behavior. The description adds valuable context beyond annotations: 'Free, no account,' which addresses authentication needs, and 'real row counts...the counties each one actually covers,' which sets accuracy expectations. It also clarifies the workflow role of the tool.

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 core purpose, followed by workflow guidance, data scope, and practical examples. Every sentence earns its place; the structure is tight and scannable without 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 the simple optional parameter, strong annotations, and existing output schema, the description provides everything an agent needs: what the tool does, what data it covers, how it relates to its sibling, authentication posture, and example queries. No critical context 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 schema describes the single 'about' parameter with 100% coverage, including examples and the note 'Omit to list everything.' The tool description's example invocations reinforce this but do not add significant new meaning beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Lists the public-records datasets Brick & Mortar publishes for the seven-county Minneapolis-St. Paul metro.' It further distinguishes itself from the sibling twin_cities_records by saying 'Call this FIRST to learn what can be answered, then call twin_cities_records to ask it.'

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 workflow guidance: call this tool first to discover what data exists, then call twin_cities_records to query it. It also provides concrete example invocations showing the kinds of questions this tool can answer, making when-to-use unambiguous.

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 behavior beyond annotations: it states the response includes the true matching row count, up to six example rows, and a link to the complete file. It also clarifies that the tool works over joined public records, which helps set expectations about data scope.

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 core purpose, then gives a compact behavioral summary and useful example queries. It is longer than minimal but each section serves a purpose—especially the examples, which make the tool's usage concrete. It could be tightened slightly, but there is no wasted 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?

Given five parameters, an output schema, and safety annotations, the description covers the main ambiguities: how to target one property vs. the market, what response to expect, and what kinds of questions are answerable. It does not describe the within_ft parameter directly, but the schema covers that, and the half-mile example implies radius usage. Overall, an agent has enough to 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?

Schema description coverage is 100%, so the schema already documents all five parameters. The description goes beyond the schema by explaining the address parameter's optionality and disambiguation rule (include the city for common street names), and by illustrating radius-based queries. This adds practical meaning that the bare schema entries do not fully convey.

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 answers questions about the Minneapolis-St. Paul metro from joined public records, with concrete examples of property sales, ownership, contamination files, and census data. It is clear what the tool does, though it does not explicitly differentiate itself from sibling tools like data_source_atlas or twin_cities_datasets.

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 guidance on how to scope queries: provide an address for one property and its surroundings, or omit it for the whole market cut. Example invocations illustrate appropriate use. It does not, however, explicitly say when to use this tool instead of a sibling or mention prerequisite steps such as calling twin_cities_datasets first.

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