GlobalSource Partners MCP Server

search_research_posts

Read-onlyIdempotent

Search published research posts associated with one or more research entities.

This tool requires research entity UUIDs. If only entity names are known, first call search_research_entities to obtain candidate research entities and their UUIDs.

Use only entity_uuid values copied exactly from search_research_entities results. Never infer, guess, construct, or transform UUIDs from entity names.

Use this tool only after selecting the most appropriate research entity from the search_research_entities results.

Examples:

To find research about "United States", first call search_research_entities with "United States", review the returned matches, select the most appropriate entity, and then call this tool with the selected entity_uuid.
To find recent research about multiple entities, pass all selected entity_uuid values in research_entity_uuids.
To retrieve the next page of results, pass the previous response's next_cursor as cursor.

Results can be filtered by publication date and retrieved using cursor-based pagination.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of posts to return. Minimum 1, maximum 50, default 25.
`order`	No	Sort results by publication time. Use 'published_descending' for newest first or 'published_ascending' for oldest first. Default is published_descending.
`cursor`	No	Pagination cursor returned by a previous response. Use this to retrieve the next page of results.
`published_after`	No	Only return posts published after this date and time (ISO 8601 format).
`published_before`	No	Only return posts published before this date and time (ISO 8601 format).
`count_total_results`	No	Whether to include the total number of matching posts. Use false unless the total count is specifically needed. Calculating the total count may increase response time for large result sets.
`research_entity_uuids`	Yes	One or more research entity UUIDs to search against. This field is required. At least one research entity UUID must be supplied. Do not pass entity names. If the user provides entity names rather than UUIDs, first call the "search_research_entities" tool and use the returned UUIDs from that tool.

Output Schema

TableJSON Schema

Name	Required	Description
`limit`	Yes	The maximum number of research posts requested.
`order`	Yes	The sort order applied to the results.
`results`	Yes	The research posts matching the supplied research entities and filters, ordered according to the requested sort order.
`next_cursor`	Yes	An opaque pagination cursor. Supply this value in a subsequent request to retrieve the next page of results. Clients should not attempt to interpret or modify the cursor value. If this field is null, there are no additional pages of results.
`published_after`	Yes	The effective lower publication timestamp used for the search. If no lower publication date filter was supplied, this defaults to the earliest date from which research is available.
`published_before`	Yes	The effective upper publication timestamp used for the search. If no upper publication date filter was supplied, this defaults to the current date and time.
`research_entities`	Yes	The research entities used to filter the search results.
`total_results_count`	Yes	The total number of matching research posts before pagination was applied. Returned only when count_total_results was requested with true; otherwise null.

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: it only searches published posts, strictly requires exact UUIDs (never inferred), and supports cursor-based pagination and date filtering. 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.

Conciseness4/5

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

The description is well-structured: summary first, then prerequisites, followed by examples. It is somewhat lengthy and repeats the UUID caution, but this is justified for a tool with a high-risk misuse pattern. Every section serves a clear purpose.

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

Completeness5/5

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

Given the tool's complexity (prerequisite entity search, exact UUID requirement, multiple filters, pagination), the description covers all necessary usage context: how to prepare inputs, what to do with entity names, how to paginate, and what filtering capabilities exist. The output schema handles return-value documentation, so nothing important is missing.

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

Parameters3/5

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

The input schema already provides 100% coverage with descriptions for all 7 parameters. The description reinforces critical UUID handling and cursor semantics, but does not add substantial meaning beyond the schema, so the baseline of 3 is appropriate.

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

Purpose5/5

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

The description clearly states the tool searches published research posts associated with one or more research entities. It distinguishes itself from siblings: search_research_entities finds entities, while read_research_post and read_research_author read specific records.

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

Usage Guidelines5/5

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

Provides explicit workflow: if only entity names are known, first call search_research_entities; use exact UUIDs from that result; select the most appropriate entity before searching posts. It also includes concrete examples and pagination guidance, 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.

All GlobalSource Partners MCP Server tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0

Disambiguation5/5

Each tool targets a distinct resource and action: search entities by name, search posts by entity UUIDs, read a post by UUID, and read an author by UUID. The descriptions clearly delineate their purposes and include explicit cross-references, making misselection unlikely.

Naming Consistency5/5

All tool names follow a strict verb_noun pattern with a consistent 'research_' prefix: read_research_author, read_research_post, search_research_entities, search_research_posts. The verbs 'read' and 'search' accurately reflect retrieval operations, and naming is uniform.

Tool Count5/5

With 4 tools, the server is well-scoped for a read-only research retrieval domain. Each tool serves a necessary function in the entity-based research workflow, and the count is neither thin nor bloated.

Completeness5/5

The tool set covers the full research retrieval lifecycle: entity discovery (search_research_entities), content discovery (search_research_posts), and content retrieval (read_research_post, read_research_author). The dependency hints ensure agents can complete workflows without dead ends, and the read-only scope needs no CRUD operations.

Resources

Need Help?