Skip to main content
Glama

Search research projects

search_projects
Read-onlyIdempotent

Search project names, descriptions and membership. Returns cited summaries and item counts; use get_project for detail.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_projects"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoDefault 25, max 100
memberNoA project member's name; either order works
offsetNo
keywordNoEvery word must occur in the name, an acronym or the description; quote a phrase
universityNoubt | unilag | ujkz | ufba | external — code or name. A data facet, not a full AMRC list
institutionNoFunding/affiliated institution name, partial
research_sectionNoName or id, e.g. 'Knowledges'
principal_investigatorNoA PI name; either order works ('Erdmute Alber' finds 'Alber, Erdmute')

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / keyword / description
      Previous value: -"Matches the project name, an acronym or the description"New value: +"Every word must occur in the name, an acronym or the description; quote a phrase"
  2. Changed1 schema field changed
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
  3. Changed1 schema field changed
    • removedInput schema / properties / limit / maximum
      Removed value: -9007199254740991
  4. Changed1 schema field changed
    • changedInput schema / properties / principal_investigator / description
      Previous value: -"A PI name; either order works ('Oliver Baumann' finds 'Baumann, Oliver')"New value: +"A PI name; either order works ('Erdmute Alber' finds 'Alber, Erdmute')"
  5. Changed8 schema fields changed
    • addedInput schema / properties / institution / maxLength
      Added value: +1000
    • changedInput schema / properties / keyword / description
      Previous value: -"Matches the project name or description"New value: +"Matches the project name, an acronym or the description"
    • addedInput schema / properties / keyword / maxLength
      Added value: +1000
    • addedInput schema / properties / member / maxLength
      Added value: +1000
    • addedInput schema / properties / principal_investigator / maxLength
      Added value: +1000
    • changedInput schema / properties / research_section / description
      Previous value: -"e.g. 'Knowledges', 'Moralities'"New value: +"Name or id, e.g. 'Knowledges'"
    • addedInput schema / properties / research_section / maxLength
      Added value: +1000
    • addedInput schema / properties / university / maxLength
      Added value: +1000
  6. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds value with 'Returns cited summaries and item counts', telling the agent what the response contains even though no output schema exists; pagination behavior is left unmentioned.

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

Conciseness5/5

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

Two short clauses with no filler; the search scope and the returned artifacts come first, and the sibling routing clause is placed last where it belongs.

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?

With eight optional parameters, high schema coverage, and no output schema, the description supplies what is missing – searchable fields and response contents. Only pagination/limit behavior and result ordering are unspecified, which is a minor gap given the schema's limit/offset descriptions.

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 88%, so the eight filter parameters are already well documented in the schema, including the university code list and the PI name-order hint. The description adds only the notion of 'membership' matching, which maps loosely to the member parameter, so the schema does the heavy lifting.

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 uses a specific verb ('Search') and enumerates the searchable fields – names, descriptions, membership – so the resource is unambiguous. It also points to get_project for detail, which separates it from the detail-retrieval sibling, though it does not distinguish itself from the generic 'search' sibling.

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

Usage Guidelines4/5

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

It states the operative alternative ('use get_project for detail'), giving a clear search-vs-fetch rule. There is no explicit statement of when not to use it or how the many facet parameters should be combined to narrow a query, which keeps it from a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.