DropshippingLeads MCP

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

The annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value comes from the data-completeness caveat: no private database and no guarantee that all categories are represented. That caveat, which shapes how far an agent should trust the result, is exactly the kind of context the annotations cannot supply.

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 short sentences that lead with what is returned and then add caveats. They contain no filler, though the sentence about downstream use of category names is worded awkwardly and could be stated more tightly.

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?

There is no output schema, so the description must carry the burden of the return values; it enumerates the returned content (status, release info, category names and counts), which is adequate for a metadata-read tool. The exact response shape is still left implicit, but nothing critical to call it 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?

This tool takes zero parameters, so the baseline score of 4 applies. The description adds no parameter detail, but there is nothing to 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 combination ('Read public dataset status, published release information, English category names and counts'), which is far more informative than a tautology. The scope is clearly distinct from the merchant and methodology siblings, though it never names them to make the contrast explicit.

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 a downstream usage hint ('Use the returned category names for searching') and one exclusion ('does not describe the private commercial database'). However, it never says when an agent should call this tool versus get_methodology or search_merchants, so the trigger condition is only implied.

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 readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value beyond them: results are limited to the activated public dataset, and a not_ready state is explicitly distinguished from an unknown record — a behavioral nuance not inferable from any structured field.

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 zero filler, and the prerequisite lookup source is front-loaded before the caveats about dataset scope and result states.

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 single-parameter read tool with full annotation coverage and no output schema, the definition covers preconditions, data scope, and the meaningful error/empty distinction. It stops short of characterizing the returned record's shape, which is a minor residual 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 0%, so the description must carry the parameter burden. It does the essential part by specifying the ID's provenance (it comes from search_merchants), which is the key semantic an agent needs; it does not describe format or length constraints, but those are already in 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?

States a specific verb and resource ('Read one ID') and ties it directly to the sibling that produces that ID ('returned by search_merchants'), so an agent can tell the lookup apart from the search without opening either schema. The scope 'activated public dataset' further narrows what record is returned.

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 phrase 'one ID returned by search_merchants' establishes the prerequisite flow: get an ID from search, then read it here. It does not mention the other siblings (get_data_coverage, get_methodology), so it lacks explicit exclusion guidance, but the intended usage context is 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 establish read-only, idempotent, non-destructive, closed-world behavior, so safety is covered. The description does add substantive context beyond that—provenance caveats, unverified company size and buying intent, unknown dates, code-only MIT licensing, and the free-vs-private quarterly batch distinction—but it presents these as topics rather than stating what the response will actually say or how the agent should treat those caveats.

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 entire description is one ~60-word sentence enumerating roughly a dozen unrelated topics with no grouping, ordering, or front-loading of the most important point. It reads as an SEO keyword dump rather than agent-facing guidance, and the key takeaway has to be dug out.

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

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

With no parameters and no output schema, the description must carry the load, and it does signal the breadth of content (field meanings, data-use terms, licensing, provenance, caveats). What it omits is the routing information—when to call this versus get_data_coverage—and any sense of what the returned methodology looks like, leaving a visible gap for a reference 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?

The tool takes zero parameters, so the baseline is 4; there is nothing the description needs to disambiguate on input and nothing it incorrectly implies.

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 verb 'Explain' plus the subject 'how DropshippingLeads supports... research' gives a rough sense of a reference/methodology read, but the purpose is buried under a 15-clause topic list. It never distinguishes itself from the closest sibling, get_data_coverage, so an agent cannot tell which of the two to open for coverage vs. interpretation questions.

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?

There is no when-to-use or when-not-to-use guidance, no mention of get_data_coverage as the alternative for coverage questions, and no stated trigger such as 'call this before interpreting results or citing license terms'. The topic list implies usage but never states it.

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

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

Annotations already declare read-only, idempotent, closed-world, non-destructive, so the bar is lower; the description still adds real behavioral context: hard 50-record cap, accompanying dataset status in the response, explicit unverified fields, and the activation-only data boundary.

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?

Dense but front-loaded: purpose first, then filter semantics, then limits and caveats. Every clause carries information, though the long compound sentences could be split for faster scanning.

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

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

With no output schema, the description usefully states that results are capped and include dataset status; with only one documented parameter it compensates well elsewhere. The unaddressed offset parameter is the main remaining gap for a 5-parameter 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 coverage is only 20% (only category documented), so the description must compensate and largely does: keyword matching covers both English and Chinese names, category accepts the English coverage name or Chinese alias case-insensitively, market is explicitly a sales-market label, and a 50-record ceiling is stated. Offset is the one parameter left unexplained.

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 (search merchant records in an activated public dataset) plus the concrete query dimensions: text, category, and sales-market label. It also carves out that market is a sales-market label, not a business-location filter, which prevents a common misread.

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?

Gives useful scope conditions — only activated public records, no private database, no live crawling, unverified size/use/intent — so the agent knows what data is valid. However, it never states when to prefer this over siblings like get_merchant or get_data_coverage, and the coverage dependency is only implied through the category parameter.

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