Skip to main content
Glama
wos-mcp-bridge

wos-mcp-bridge

Search Wos

search_wos
Read-onlyIdempotent

Search one page of Web of Science Core Collection for bibliographic metadata, authors, DOIs, and citation counts using advanced query syntax and sorting.

Instructions

Search one page of WoS Core Collection and return bibliographic metadata.

query: WoS advanced syntax, e.g. TS=(canine AND lung) AND PY=(2020-2026). limit: 1-50 records. page: starts at 1. No automatic pagination or retries. sort: RS+D relevance; PY+D newest; LD+D recently indexed; TC+D most cited (citation sorting depends on entitlement). Returns the exact query, total, DOIs, authors, available citation counts, and retrieval/quota information.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_wos"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoOne-based WoS page; no automatic pagination.
sortNoSort code: RS relevance, PY year, LD indexed date, TC citations; D descending, A ascending.RS+D
limitNoMaximum records in this explicit page.
queryYesWoS advanced search across available Core Collection disciplines; no control characters.

Output Schema

NameRequiredDescriptionDefault
sortYes
queryYes
resultsYes
databaseYes
metadataYes
retrievalYes
limitationsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: no automatic pagination or retries, citation sorting depends on entitlement, and the response includes quota/retrieval information. This is meaningful disclosure an agent could not get from the annotations alone.

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 core purpose is front-loaded in the first sentence, followed by compact per-parameter notes and sort codes. Some lines duplicate the schema (limit range, page starting at 1), but there is no padding or vague filler.

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

Completeness4/5

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

For a read-only, paginated search tool with a full schema and an output schema, the description covers the essentials: syntax expectations, page/limit semantics, sort behavior, and the no-auto-pagination caveat. The only omission is explicit routing against sibling search tools.

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?

Schema description coverage is 100%, so the schema already documents query syntax, limit bounds, page numbering, and the sort enum. The description largely restates these (limit 1-50, page starts at 1) and maps sort codes, which the schema also explains; its only added nuance is the entitlement caveat on citation sorting. Baseline 3 applies.

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

Purpose4/5

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

The description opens with a specific verb and resource ('Search one page of WoS Core Collection and return bibliographic metadata'), which tells an agent exactly what is queried and that results are page-bounded. It does not explicitly differentiate itself from the sibling 'search' or 'search_literature' tools, so it falls short of a 5.

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

Usage Guidelines3/5

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

It supplies operational context (advanced-syntax query example, limit range 1-50, page starts at 1, no automatic pagination or retries), which is genuinely useful for calling it correctly. However, it never states when to choose this tool over 'search' or 'search_literature', so guidance is implied rather than explicit.

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