Crawdar Business Research

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

Annotations already indicate destructiveHint=true and idempotentHint=true. The description adds specific behavioral context: it defines which states are actionable (queued or running) and which are not (completed/failed). This clarifies the exact boundary of the destructive effect and aligns with the idempotent hint, without contradicting any annotation.

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 concise sentences. The primary action is front-loaded in the first sentence, with the state restriction in the second. Every word adds value; there is no fluff, repetition, or tangential 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 simple cancellation tool with an output schema and annotations covering safety, the description conveys the core operation and state constraints well. However, the lack of parameter explanations is a significant gap that leaves an agent uncertain about how to supply the required 'id' and 'jobToken'. This makes the tool incomplete for correct invocation despite the otherwise simple scope.

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 what 'id' or 'jobToken' mean or how to obtain them. The parameter names offer minimal hints ('id' suggests a job ID, 'jobToken' suggests a token), but there is no semantic guidance on required format, purpose, or relationship between them. The description fails to compensate for the complete lack of schema-level documentation.

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 verb 'cancel' and the resource 'lead search job', immediately distinguishing it from sibling tools like start_lead_search or refine_lead_search. It adds the crucial constraint that only queued or running jobs can be cancelled, and completed/failed are immutable, which precisely scopes the tool and prevents misuse.

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 explicit context on when to use the tool: only for queued or running jobs. It clearly states that completed and failed jobs are immutable, implying they should not be targeted. However, it does not directly point to alternatives (e.g., retry_lead_search for failed jobs), so the exclusion guidance is present but not fully 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?

The annotations already declare read-only, idempotent, and non-destructive behavior, and the description adds a behavioral note about not consuming a search. Together, these provide complete transparency about side effects and input handling.

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, each conveying essential information without fluff. It is well-structured and directly states the tool's purpose and a key constraint.

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 specifies the types of information provided (result semantics, limits, interface URLs, safe operating guidance), which gives a complete picture of what the tool returns. Combined with the annotations, the tool's context is fully covered.

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, so the schema coverage is complete. The baseline for no parameters is 4, and the description does not need to elaborate on any parameter semantics since there are none.

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 provides result semantics, limits, interface URLs, and safe operating guidance, which is specific and distinguishes it from the sibling search tools. It is concise 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 explicitly notes that the tool does not consume a search, which clarifies it is not for search operations and guides when to use it (for explanations) versus the search-focused siblings. This is a clear usage hint.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds non-obvious behavioral context: jobToken must be kept private and nextCursor must be passed back unchanged. 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?

Two short sentences with no filler. The primary operation is front-loaded, and the security/pagination instructions are concise and actionable.

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 covers return values, and annotations cover the read-only/idempotent behavior. The description covers the two non-obvious operational rules: token privacy and cursor reuse. It is slightly incomplete on when status vs page is returned and the role of id, but it is sufficient for a paginated read 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 low, so the description must compensate. It adds meaning for jobToken ('keep private') and cursor ('pass nextCursor back unchanged'), but id is left unexplained and view/limit rely on schema constraints. Compensation is partial.

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

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

The description uses a specific verb ('Read') and names the resource ('job status or one cursor-paginated result page'), making the tool's purpose clear. It differentiates from sibling mutation tools like start/cancel/retry/refine, though it does not explicitly name an 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 description implies this tool is for reading an existing lead search job or page, which distinguishes it from creation/cancellation/retry siblings. However, it never explicitly states when to use this tool versus alternatives or 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?

The description says 'Create a new private search job', implying a write operation, but the annotation readOnlyHint is true, which is a direct contradiction. No other behavioral details are provided beyond the annotation.

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 concise sentences with the core action first. No wasted words, and the key constraint ('original job stays unchanged') is included.

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 8 parameters, 2 required, and zero schema description coverage, the description leaves too much to inference. It lacks details on prerequisites (e.g., needing a completed job's token) and the annotation contradiction further undermines completeness.

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 only mentions 'brief or criteria' but does not identify required parameters like id and jobToken or clarify their roles. The schema provides names but no 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 description clearly states the action ('Create a new private search job') and the resource ('a completed job'), distinguishing it from starting fresh or retrying by specifying 'by changing the brief or criteria' and noting the original job stays unchanged.

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 clearly indicates this is for refining a completed job, which implies the use case. However, it does not explicitly exclude alternatives like start_lead_search for new searches or retry_lead_search for retrying, so it lacks explicit when-not 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 and destructiveHint=false, so the agent knows it's safe. The description adds 'evidence-backed' implying source links, but doesn't specify pagination, result limits, or diagnostics behavior. It goes slightly beyond annotations but not substantially.

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, front-loaded sentence that immediately communicates the core transformation. Every word adds value, and there is zero padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has only one required parameter and rich schema descriptions for optional ones, plus an output schema. The description sufficiently covers the primary workflow (put everything in the brief), so additional details would be redundant for this moderate complexity.

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 86%, so parameters are well-documented. The description reinforces the brief's role but adds no new semantics for limit, offset, fields, or output. It meets the baseline without exceeding it.

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

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

The description clearly states the tool converts a natural-language brief into evidence-backed business results, which is specific and differentiates it from sibling tools like search_businesses that likely use structured queries. The verb 'Turn' and resource 'business results' are precise.

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 usage context: use this tool when you have a natural-language brief, and it instructs to put business type, geography, signals, and exclusions directly in the brief. However, it does not explicitly name alternative tools or state when not to use this tool, which would have earned 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?

The description says 'Create a replacement job,' which is a write/side-effect operation, yet annotations declare readOnlyHint=true and destructiveHint=false. This directly contradicts the annotations, and the contradiction rule requires a score of 1.

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

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

Two sentences, both earning their place: the first states the core action and trigger, the second adds the audit-relevant behavioral note. Nothing is redundant or padded.

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?

Complexity is low (two simple params, an output schema exists), and the description covers the purpose, trigger, and a key behavior. However, jobToken is left entirely unexplained and the readOnlyHint contradiction creates ambiguity about whether the operation has side effects, so it is only minimally viable.

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 burden of explaining 'id' and 'jobToken.' It only weakly implies that id refers to the prior job and says nothing about jobToken (its format is 20-100 characters for a reason), so the agent is left guessing.

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

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

The description uses a specific verb and resource — 'Create a replacement job' — and gives the trigger condition: 'when a prior job failed or exceeded its execution window.' This clearly distinguishes retry_lead_search from siblings like start_lead_search, cancel_lead_search, and get_lead_search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states a clear trigger condition ('failed or exceeded its execution window') that tells an agent when this tool is appropriate. It does not explicitly name alternatives or state when-not-to-use conditions, 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?

Adds valuable behavioral context beyond annotations: 'deterministic' and 'fictional' along with 'without consuming provider capacity' informs the agent that results are synthetic and cost-free. This aligns with idempotentHint and readOnlyHint, and provides extra insight about output characteristics that annotations alone do not cover. No 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?

Two sentences with no filler. The core purpose and key differentiator ('without consuming provider capacity') are front-loaded, and the usage hint follows. 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?

The tool is simple with two optional params and an output schema (which likely documents return structure). The description covers purpose and usage but lacks parameter explanations, leaving 0% schema coverage uncompensated. For a sandbox tool this may be acceptable, but an agent would benefit from knowing what 'target' and 'geography' do.

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 for parameter meaning. However, the description does not explain 'target' or 'geography' at all. The parameter names might be partially self-explanatory, but given zero schema descriptions, this is a significant gap. The description adds no parameter-level detail.

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

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

States a specific verb and resource ('return deterministic fictional businesses') and clearly differentiates from real data tools by emphasizing 'without consuming provider capacity'. The title 'Test the Crawdar contract' reinforces the testing intention, and the description names its use case clearly.

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?

Explicitly says 'Use this to test schemas, clients, and agent loops', giving a clear when-to-use. It implies a distinction from real search tools but does not explicitly name alternatives or state when NOT to use it. Still, the context is clear enough for an agent to route 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 declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the behavioral nuance that this is a structured, explicit-criteria search (not natural-language) and that qualifiers require public evidence, which aids agent behavior 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?

Two sentences with zero filler. Front-loaded with the primary action, then a clear pointer to the alternative tool. Every phrase 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 tool has an output schema and 88% parameter schema coverage, so return values and parameter formats are already documented. The description supplies the one missing piece—choosing between this and research_businesses—making the overall package complete for correct tool selection and 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 88%, so structured fields already carry most parameter meaning. Description adds a high-level framing tying 'target' and 'geography' to 'explicit' criteria and 'public-evidence requirements' to the qualifier, but these are largely reinforced by the schema descriptions rather than new information.

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 action: 'Find businesses matching an explicit target, geography, and optional public-evidence requirements.' It specifies the resource (businesses) and the structured criteria, and explicitly distinguishes itself from the sibling research_businesses tool.

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: use this tool for structured criteria, and 'Use research_businesses when you have one natural-language brief.' This directly names the alternative and its intended use case, providing clear when-to-use 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?

The description says 'Create a private search job,' implying a write operation, but annotations declare readOnlyHint=true. This is a direct contradiction. Additionally, the description adds no beyond-annotation behavior details regarding rate limits, costs, or the asynchronous nature that the title hints at. The contradiction makes this dimension score 1.

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 fluff. The core purpose is front-loaded, and the output artifact (job id, jobToken) is mentioned. It could be improved by adding usage guidance, but as far as conciseness, it is appropriate.

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 7 parameters, a complex anyOf requirement, and a low schema coverage, the description is insufficient. It doesn't explain the parameter groups or the durable nature, and it doesn't guide the agent on what 'jobToken' is for beyond a vague mention. Even though an output schema exists, the input side is severely underdocumented. The description leaves significant gaps for an agent to call this 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 only 14% (only idempotencyKey is described). The description mentions the 'brief' but does not explain the target, geography, qualifier, limit, or fields parameters. Since schema coverage is low, the description must compensate, but it provides no parameter semantics, leaving agents to guess the meaning and format of most inputs.

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

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

The description clearly states the action: 'Create a private search job from a natural-language brief.' It identifies the resource (lead search job) and the input type (natural-language brief). However, it does not explicitly contrast with siblings like search_businesses or research_businesses, so it relies on the tool name and title to hint at the distinct durable/asynchronous nature.

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 does not provide any when-to-use guidance or mention alternatives. The title mentions 'durable' but the description never explains that this tool is for long-running, retrievable searches, nor when one should choose this over search_businesses. No exclusions or alternative usage hints are given.

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