Thailand Stay Plan

Which Thai visa fits me

which_thai_visa

Read-onlyIdempotent

Use when someone asks how they can stay in Thailand or which Thai visa or route fits them, e.g. "how can I stay in Thailand for a year", "which visa do I need to retire in Thailand", "can I live in Thailand as a remote worker", "I am married to a Thai, how do I stay", "DTV or LTR or Thailand Privilege for me", "how long can I stay visa-free". Ranks the seven legal routes (30-day exemption + extension, tourist visa, DTV, Non-O retirement, Non-O marriage/Thai family, LTR, Thailand Privilege) with the same rules and ranking as the Visa Map on thailandstayplan.com: for each route whether it fits, why, what to watch, 5-year or per-trip cost, time to get it, core papers, insurance rule, and the public sources with their check date. Inputs: nationality as the user says it, age, planned stay, savings and income as numbers (Thai baht; convert other currencies at today's rate and tell the user), remote work, Thai spouse or child, budget. If nationality, age, stay or every money figure is missing, the tool returns one question to ask the user (scope needs_input); do not guess them. Thailand only. Information with sources, not legal advice; it recommends no agent, insurer or product.

Input Schema

Name	Required	Description
`age`	No	Age in years. The retirement routes need 50 or over.
`stay`	No	How long the user wants to stay in Thailand in total: under_30_days, 1_to_6_months, 6_to_12_months, or years (a year or more, indefinitely, retire, live there).
`budget`	No	frugal = lowest cost even with more paperwork; standard = cost and effort balanced (default); premium = pays for zero paperwork.
`nationality`	No	Passport nationality as the user says it: country name, adjective or ISO code, e.g. "German", "United Kingdom", "US", "Australian", "Brazil". EU countries, the UK, the US, Canada, Australia and Japan are matched to the Visa Map groups; any other nationality is ranked as "other" and told to check the 60-country visa-exemption list.
`remote_work`	No	Will the user work remotely for a foreign employer or clients while in Thailand? Default false.
`savings_thb`	No	Savings the user could move to a Thai bank, in Thai baht. Convert other currencies at today's rate first and tell the user the rate you used. 0 if none.
`thai_family`	No	Does the user have a Thai spouse or a Thai child? Default false.
`monthly_income_thb`	No	Regular income per month in Thai baht: pension, salary, rent, dividends. Convert at today's rate and say so. 0 if none.
`annual_passive_income_usd`	No	Passive income per year in US dollars (pension, investments, rent), if known: the BOI LTR thresholds are USD 40,000 and USD 80,000 a year. Give monthly_income_thb as well.

Output Schema

Name	Required	Description
`scope`	Yes	ranked = full answer; needs_input = ask the user the question first.
`routes`	Yes
`question`	Yes
`site_url`	Yes	The Visa Map on thailandstayplan.com with these answers prefilled.
`best_route`	Yes
`disclaimer`	Yes
`inputs_used`	Yes
`rules_checked`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 27, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations cover safety (readOnly, idempotent, non-destructive) but the description adds substantial behavior: the specific output fields per route, the ranking methodology and source-check dates, the needs_input scope behavior, currency-conversion narration, and disclaimers ('not legal advice', recommends no agent/insurer/product). This is rich context beyond structured fields.

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?

Front-loaded with the trigger and examples, then the return contents, then the input contract and the scope guardrail. Dense but every section earns its place; it is a long single block, which costs a point versus a tightly structured version.

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?

With an output schema present, the description still specifies the deliverable fields, the ranking source, the needs_input branch, and the legal disclaimer. Nothing an agent needs to call it correctly or interpret results 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?

Schema description coverage is 100%, so the schema already documents every parameter, including the 50+ retirement rule, enum meanings, and the currency-conversion instruction. The description largely restates these inputs and adds only the missing-figures rule, so baseline 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?

States a specific verb and resource: ranks seven named legal routes and explains fit, cost, timing, papers, insurance and sources, matching the Visa Map ranking. An agent can tell exactly what the tool produces versus a generic search. Scope ('Thailand only') is stated explicitly.

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?

Opens with an explicit 'Use when...' trigger plus five concrete example user questions, and defines a when-not-to-proceed case: if nationality, age, stay or money figures are missing, return one question instead of guessing. Alternatives and exclusions are implicit only because no sibling tool exists.

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

All Thailand Stay Plan tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?