Skip to main content
Glama

AY Grants

Eligibility screen (Taiwan)

screen_grants
Read-onlyIdempotent

Taiwan grants open now, opening soon or with no fixed deadline, screened by the rules of the free check at https://twgrants.ayskilllab.com/check: who can apply, then the county, then the limits a notice states in so many words (years since founding, capital, employees, the SME standard). Each row says why it is listed, with the notice's sentence, and is one of fits, unconfirmed (the notice doesn't say who or where) or may_not_fit (a stated limit disagrees; it can belong to one sub-item, so read the notice). Leave out what you don't know; it is then not compared. Reasons are in Chinese, as the notices are. Up to 10 rows an answer and 3 pages; 300 rows a day per address.

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": {
      "organisation_type": "<organisation_type>"
    },
    "name": "screen_grants"
  }
}

Input Schema

NameRequiredDescriptionDefault
alsoNoIdentities some grants are only for: 原住民 (indigenous person or group), 農漁民 (farmer, fisher, farmers' or fishers' association).
pageNo
countyNoWhere the applicant is registered. Grants open to the whole country count too.
includeNoWhich results to list; fits_and_unconfirmed unless you say. The counts always cover all three.
employeesNo
capital_twdNoPaid-in capital in NT$ (元), not 萬.
founded_yearNoYear founded, Western (2022) or ROC (111).
organisation_typeYes企業 = company or business, 個人 = individual, 團體 = association or co-operative, 法人 = foundation or incorporated association, 學校 = school, 政府機關 = government body.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Beyond the annotations (which already mark it read-only, idempotent, non-destructive, closed-world), the description discloses concrete operational limits: 10 rows per answer, 3 pages maximum, 300 rows per day per address. It also explains output semantics — each row carries a verdict of fits/unconfirmed/may_not_fit plus the notice's own sentence, with reasons in Chinese — and warns that may_not_fit may apply to only one sub-item, which is genuinely useful behavioral context.

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?

Information is front-loaded — the screening purpose and ordering come first, followed by result labels, then limits. Sentences are dense and somewhat run-on, but nearly every clause carries useful content; only the URL reference and the parenthetical sub-item caveat could be tightened.

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 an 8-parameter tool with no output schema, the description does the heavy lifting: it defines the three verdict labels, explains the per-row reason field and its language, and covers pagination and rate caps. Remaining gaps are minor — it does not state total result counts semantics or row ordering beyond the screening order.

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

Parameters4/5

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

Schema coverage is 75%, and the description still adds meaning: it explains that screening proceeds by applicant identity, then county, then stated limits (founded years, capital, employees, SME standard), mapping the parameters to the verdict logic rather than just restating them. It also clarifies that omitted parameters are simply not compared, which the schema does not say.

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 gives a specific verb and resource ('Taiwan grants ... screened by the rules of the free check') and enumerates the screening order (who can apply, county, then stated limits), which clearly marks this as a fit-scoring tool rather than a plain listing. It does not name any sibling such as search_open_grants, so differentiation is inferable but not explicit.

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?

Usage is implied through the screening criteria and the note 'Leave out what you don't know; it is then not compared', which tells the agent how to behave with incomplete applicant data, plus the default for the include filter. However, there is no explicit statement of when to choose this over search_open_grants or get_grant, nor any when-not guidance.

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.

Resources