eBay MCP

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

With no annotations present, the description carries the full burden and does disclose that this is a SerpAPI-backed fetch and enumerates the returned sections (product_results, seller_results, related_products), which is meaningful since there is no output schema. It stops short of disclosing failure behavior (item not found, invalid id), SerpAPI quota/credit consumption, or the result-cache interaction that no_cache implies.

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 tight sentences, front-loaded with the verb and resource, then the required input, then the return shape. Every sentence contributes new information with no repetition 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 7-parameter, no-annotation, no-output-schema tool, the description supplies the required-input provenance, marketplace guidance and a return-value inventory, which is close to sufficient. Missing error/quota and cache semantics keep it from being fully complete, though no output schema means the return-value summary is genuinely needed and present.

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 all seven parameters are already documented in the schema and the baseline is 3. The description adds only a little: it restates product_id provenance (near-verbatim with the schema) and explains the intent behind ebay_domain ('match the marketplace the item was found on'), but says nothing about lang, locale, shipping_country, no_cache or zero_trace.

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 ('Get full details for a single eBay item') plus the upstream engine, and the word 'single' plus the product_id sourcing rule cleanly separates it from the ebay_search sibling. An agent can tell which of the two to call without opening either schema.

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 explains the pre-condition for calling: product_id must come from an ebay_search result's product_id field or an /itm/<id> URL, and ebay_domain should match the marketplace the item was found on. That is a clear usage context, but it never states what this tool is not for (e.g. keyword browsing) beyond implying it via the id requirement.

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 the burden and does well: it discloses the upstream dependency (SerpAPI), the shape of the return (organic_results fields, categories, related_searches, pagination), that results may come from a server-side cache (`no_cache`), and that `zero_trace` is enterprise-only. It omits rate limits, quota costs, and error 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?

The search mechanics and the `ebay_product` handoff are front-loaded, and every sentence conveys usable information. It is dense and parenthetical-heavy, and the "and more" filter roll-call mildly duplicates the schema, but nothing is truly wasted.

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 20-parameter tool with no annotations and no output schema, the description covers the gaps that matter: return structure, currency semantics, caching, and the cross-tool workflow. There is nothing further an agent needs in order 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 coverage is 100%, so baseline is 3; the description earns above that by explaining intent, not just existence — `_nkw` is "what you'd type in eBay's search box," prices are in the marketplace currency set by `ebay_domain`, and `product_id` is the bridge to `ebay_product`. It still doesn't meaningfully frame the less obvious knobs (`_blrs`, `_salic`, `_stpos`, `_dmd`).

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 — live eBay listing search via SerpAPI engine `ebay` — and immediately differentiates from its only sibling by naming `ebay_product` as the follow-up for full item detail. An agent can distinguish the two without opening either schema.

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 concrete use conditions: supply `_nkw` and/or `category_id`, apply filters for price/condition/format/seller, and hand off `product_id` to `ebay_product`. What's missing is any explicit "don't use this for X" exclusion or cost/latency caveat when calling live versus cached.

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