ablakarajanlat.hu Nyílászáró MCP

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

Annotations only declare the generic profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false); the description adds non-obvious behavior beyond them: a hard 5-attempt lockout that blocks the request, and the fact that the quote request is only forwarded to staff after successful confirmation. These are exactly the operational risks an agent needs before calling.

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

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

The critical constraint (do not guess, lockout risk) is front-loaded and the English sentence is a tight condensed summary rather than a full duplication of the Hungarian. The bilingual format costs some length, but no sentence is pure filler.

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

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

For a two-parameter mutation with no output schema, the description covers prerequisites, input provenance, failure behavior, and post-success effect, which is close to everything needed to call it correctly. It stops short of saying what the immediate response contains (e.g., confirmation payload vs. error shape), a minor gap given no output schema exists.

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

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

Schema coverage is 100%, so both parameters are already documented, and the description mostly reinforces the schema (code comes from the user's mailbox, leadId comes from the request_quote response). It adds the meaningful constraint that the code must be obtained from the user rather than invented, which is behaviorally useful but largely duplicative of the schema wording.

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

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

States a specific verb+resource ('redeem the 6-digit email code') and explicitly positions itself as 'Step 2 of request_quote', which cleanly separates it from the sibling request_quote (step 1). The downstream effect ('after successful confirmation the request reaches staff') further pins down what the call accomplishes.

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

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

Gives explicit when-to-use (second step of request_quote, after the user received the code by email), explicit source for the input (ask the user, it is in their mailbox), and an explicit prohibition with consequence (never guess or brute-force — 5 failed attempts lock the request). This is the full when/when-not pattern.

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

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 goes further by disclosing that the price is computed live, matches the Genesis editor calculator, is based on a fixed base configuration (Rehau Smart 70 tilt-and-turn; IDEAL 4000 door), and is only finalized after an on-site survey — real behavioral context. It does not describe what the response contains (breakdown, currency, validity).

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

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

The purpose is front-loaded in the first clause and the routing hint to list_inventory is placed near the caveats. It is somewhat dense and partly repeats itself across the Hungarian and English halves, which costs a little efficiency but keeps the key constraints intact.

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

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

With 6 parameters, no output schema, and simple read-only annotations, the description covers the essentials: what is priced, on what base specification, and how reliable the number is. The notable omissions are the currency and the contents of the returned estimate, which an agent would still have to discover from the response.

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

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

Schema description coverage is 100%, so all six parameters are already documented in the schema, making 3 the baseline. The description adds configuration context (which profile and opening type the base price assumes, two-sash above 130 cm) but says nothing about how color, glazing or quantity affect the quoted figure, so it does not meaningfully deepen parameter meaning.

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

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

The description names a specific verb+resource: a gross (VAT-inclusive) price estimate for custom-size (made-to-measure) plastic windows or doors. It immediately rules out the sibling case by stating that stock CanDo doors are priced separately via list_inventory, so an agent can distinguish this tool from its siblings without opening any schema.

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

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

Usage context is clear: call it for one-off, non-SKU custom sizes, and route to list_inventory for stock doors at fixed prices. It also signals this is an indicative figure refined after an on-site survey, which implicitly positions request_quote/confirm_quote as the binding path, but it never names those siblings or states the exclusion explicitly.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds value beyond that by stating the data is real-time and includes gross/retail prices and stock quantities — i.e., what the agent will actually observe. It omits any note on result size, pagination, or whether the catalog is filtered to 'standard' items only in a way that excludes configurable products.

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

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

Two tight sentences, front-loaded with the core scope (in-stock, standard, real-time price and inventory). The content is fully duplicated across the Hungarian and English sentences, which is presumably deliberate for bilingual callers but is technically redundant text.

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

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

For a zero-parameter, read-only listing tool with no output schema, the description is nearly sufficient: it tells the agent what entities come back and which fields matter (gross price, stock). The remaining gap is that it does not describe result shape, ordering, or size, which the absent output schema would otherwise have to carry.

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

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

There are zero input parameters, which normally gives a baseline of 4. The description does clarify the implicit semantics — no filtering arguments exist because the tool always returns the whole ready-stock set with prices and stock — but it never explicitly says 'takes no arguments / returns everything', so it adds only modest meaning on this dimension.

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

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

The description names a specific verb ('Listázza'/'Lists') and a precisely scoped resource: only currently in-stock ('RAKTÁRON') standard windows/doors and accessories. It also says what the listing carries (real-time gross price and stock level), which separates it from the quote-oriented siblings. It stops short of naming a sibling or explicitly contrasting with get_price_estimate/request_quote, so it is clear but not maximally differentiated.

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

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

Usage is only implied: the emphasis on 'ready-stock' and 'real-time' signals this is the browse/availability tool to consult before quoting, which is a meaningful implicit scope restriction. However, there is no explicit 'use this when...' or 'do not use this for pricing a specific configuration — use get_price_estimate instead' routing, and no prerequisites are stated.

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

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, non-idempotent, non-destructive): it discloses the emailed 6-digit code, that the request only reaches staff after confirmation, that staff call back at the supplied phone number, and that fabricated data is rejected and unconfirmed requests are lost. This is exactly the extra context annotations cannot convey, though the pre-confirmation lifecycle state (pending vs. discarded) could be stated more precisely.

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

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

Front-loaded with the key workflow and constraints, but the final English sentence fully duplicates the Hungarian paragraph, and heavy all-caps emphasis throughout adds length without new information. The core message could be delivered in roughly two-thirds the space.

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

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

No output schema exists, and the description covers everything an agent needs: what happens on success, what the required next call is, what failure looks like (rejected data, lost request), and what real-user input is mandatory. Nothing material is missing for a 6-parameter, 3-required write tool.

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

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

Schema coverage is 100%, so baseline would be 3; the description adds the consequence that invented values are rejected by the system and that the email field is the code destination and phone the callback number. Most of this mirrors the schema text, so the added value is modest rather than substantial.

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

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

States a specific verb and resource (quote request submission) plus its defining constraint: two-step email verification. It explicitly separates itself from the sibling confirm_quote (the second step) and implicitly from get_price_estimate/list_inventory by describing a real customer callback workflow.

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

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

Gives explicit when-to-call conditions (only if the user expressly asked and supplied their own real name, phone and email), the mandatory follow-up action (call confirm_quote with the 6-digit code), and when-not (never use placeholder/demo data). The exclusion of test data is stated as a hard rule with a stated consequence.

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