buyer-intelligence

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

With no annotations, description carries full burden. It discloses that the tool returns a score and evidence chain, and lists data sources. However, it does not mention safety (read-only/non-destructive), authentication needs, or potential rate limits. The description does not contradict any implicit behavior.

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?

Single sentence is concise and front-loaded with purpose. It packs multiple intelligence sources without redundancy. Only minor improvement could be breaking into clearer sections.

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 3 parameters, 100% schema coverage, no output schema, description adequately explains what it does and what it returns. However, missing details like output structure or evidence chain format reduce 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 100%, meeting baseline. Description adds slight context by stating it provides company intelligence, but does not elaborate on parameter syntax or constraints beyond schema definitions.

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

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

Description clearly identifies the tool as providing deep company intelligence for a buyer, listing specific data sources (corporate registry, customs, supply chain, decision-maker profiling) and output (0-100 score with evidence chain). This distinguishes it from sibling tools like find_buyers or enrich_buyer_contact.

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?

No explicit guidance on when to use this tool versus alternatives (e.g., find_buyers for initial search). While it implies use for analyzing a specific buyer, it does not state prerequisites, exclusions, or comparison to 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?

Without annotations, the description fully bears the transparency load. It discloses that the tool is a read operation (polling), describes possible return statuses, and indicates fresh data on completion. It also mentions it is free. No rate limits or error handling detailed, but sufficient for a simple polling 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 four sentences, front-loaded with purpose. Every sentence provides distinct information: what it does, returns, polling guidelines, and cost. No redundancy or 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 the tool's simplicity, no output schema, and no annotations, the description covers purpose, usage pattern, and termination conditions. It does not specify the exact shape of returned buyers, but that is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds marginal value by explaining the source of task_id (from find_buyers or submit_discovery_job) but does not elaborate on limit's behavior 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 uses specific verbs ('poll', 'returns') and clearly identifies the resource ('background buyer-discovery task'). It references the creating tools ('find_buyers', 'submit_discovery_job') and distinguishes this polling tool from those creation 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?

Explicitly advises when to use (after creation) and provides concrete polling strategy (exponential backoff starting ~20s) with stopping condition (completed/failed). Does not state explicit exclusions for other use cases, but the polling 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?

With no annotations, the description carries full burden. It discloses the multi-step enrichment process, fallback behavior, cost implication (Zhimao Points), and return types. However, it lacks details on potential failures, idempotency, or side effects, which would be 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 description is two sentences, front-loaded with the purpose, and every phrase adds value. No redundant or extraneous 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?

Given the tool's complexity (6-layer enrichment) and absence of output schema, the description covers inputs, process, and outputs adequately. Minor gaps exist (e.g., error handling, result format details), but overall it is sufficient for an agent.

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% with clear parameter descriptions. The tool description adds overall context (e.g., enrichment steps) but does not provide additional per-parameter meaning beyond what the schema already offers. Baseline score of 3 is appropriate.

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

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

The description clearly states the tool's function: 'Run 6-layer contact enrichment for a buyer', details the process (scraping, retry, BFS, LLM, vision, Serper fallback), and specifies outputs (email, phone, WhatsApp, decision-maker names). It is specific and distinguishes from siblings like 'find_buyers' or 'analyze_buyer_intelligence'.

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?

No explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites, when not to use, or direct comparisons with siblings. The context is implied but not stated, leaving the agent to infer appropriate usage.

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?

No annotations provided, so description carries full burden. It discloses automatic background crawl on thin coverage, free nature, and polling method. However, it does not mention auth needs, rate limits, or potential destructive actions, but for a search tool this is adequate.

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?

Four sentences, well-structured with key information upfront (search scope, returns, alternatives). No unnecessary verbiage; every sentence adds value.

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 4 parameters, no output schema, and multiple siblings, the description explains the return structure (company profiles + coverage object), acquisition task, and links to sibling tools. It could detail what company profiles contain, but overall it covers essential context.

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 baseline is 3. The description reiterates some parameters (limit defaults, max) but does not add significant new meaning beyond the schema, though it mentions behavioral context like coverage object.

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 searches over 500,000 verified importers and distributors by product category and target country, distinguishing it from siblings like check_discovery_task and enrich_buyer_contact.

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?

Provides explicit guidance on when to use the tool (searching for buyers), when to use alternatives (e.g., enrich_buyer_contact for contact details, check_discovery_task for task polling), and how to handle thin coverage via acquisition tasks.

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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It explains the tool lists pools and mentions statuses (open, filling), but lacks details on behavior like pagination, data freshness, or whether it returns non-expired pools. Adequate but incomplete.

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 packed with essential information: main action, concept explanation, and purpose. No fluff, front-loaded with the verb 'List'.

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 explains the concept well, but for a list tool with no output schema, it would benefit from mentioning what fields are returned or whether pagination exists. Adequate for a simple 2-param tool, but not fully comprehensive.

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%, with clear enum for status and optional category keyword. The description adds no extra meaning beyond the schema, so 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 clearly states it lists open collective sourcing projects (联拼宝 / Lianpinbao). It explains the concept (multiple suppliers co-sell into shared buyer pools) and the tool's purpose (find pools to join). This distinguishes it well from sibling tools like analyze_buyer_intelligence or find_buyers.

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 (to find pools to join), but lacks explicit guidance on when to use this tool versus alternatives. Sibling tools are different enough that context may suffice, but no direct 'use when' or 'do not use when' statements are present.

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?

Discloses async behavior, returns job_id, and need for polling. No annotations provided, so the description carries full burden. Could mention rate limits or idempotency, but covers essential behavior.

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

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

Two sentences, no filler. First sentence states action and result, second gives context and alternative. Efficiently structured.

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?

Covers async submission, polling, and when to use. No output schema, but description explains return value. Could mention error handling, but sufficient for typical use.

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 3. Description reiterates 'category + country' but adds no new semantics beyond what schema already provides. Keywords noted but not detailed.

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 'submit', the resource 'async batch buyer discovery job', and specifies inputs 'category + country'. It distinguishes itself from sibling 'find_buyers' by noting the auto-start behavior.

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 tells when to use this tool (forced/fresh deep crawl) and when not (since find_buyers auto-starts). Also instructs to poll with check_discovery_task after submission.

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