jmiszewicz - wycena i zapytania o strone internetowa

Brief projektu

createProjectBrief

Read-onlyIdempotent

Porządkuje dane zebrane w rozmowie w brief projektu. Nic nie wysyła i nie wymaga zgody. Zwraca brief do pokazania użytkownikowi, listę brakujących danych (missing) i następny krok. Wynik przekaż bez zmian jako brief do submitInquiry.

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": "createProjectBrief"
  }
}

Input Schema

Name	Required	Description
`city`	No	Miasto firmy (Poznań i Wielkopolska - spotkanie na miejscu możliwe; reszta Polski zdalnie)
`goal`	No	Główny cel strony
`notes`	No	Dodatkowe uwagi, inspiracje lub wymagania
`pages`	No	Łączna liczba stron, ze stroną główną (blog = 1 strona)
`budget`	No	Budżet lub przedział cenowy
`company`	No	Nazwa firmy lub klienta
`package`	No	Format z estimateWebsite (recommendedPackage), jeśli już wybrany
`deadline`	No	Oczekiwany termin realizacji
`estimate`	No	Wynik estimateWebsite w skrócie, np. „Strona firmowa + 1 moduł: 5 300-6 900 zł netto"
`features`	No	Wymagane funkcje lub sekcje
`industry`	No	Branża
`contactName`	No	Imię i nazwisko osoby kontaktowej
`contactEmail`	No	Adres e-mail osoby kontaktowej
`contactPhone`	No	Numer telefonu osoby kontaktowej
`currentWebsite`	No	Adres obecnej strony firmy, jeśli jest

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedOct 31, 2026

addedInput schema / properties / city

Added value: +{
+  "description": "Miasto firmy (Poznań i Wielkopolska - spotkanie na miejscu możliwe; reszta Polski zdalnie)",
+  "type": "string"
+}

addedInput schema / properties / currentWebsite

Added value: +{
+  "description": "Adres obecnej strony firmy, jeśli jest",
+  "type": "string"
+}

addedInput schema / properties / estimate

Added value: +{
+  "description": "Wynik estimateWebsite w skrócie, np. „Strona firmowa + 1 moduł: 5 300-6 900 zł netto\"",
+  "type": "string"
+}

changedInput schema / properties / features / description

Previous value: -"Lista wymaganych funkcji lub sekcji"New value: +"Wymagane funkcje lub sekcje"

changedInput schema / properties / goal / description

Previous value: -"Główny cel strony internetowej"New value: +"Główny cel strony"

addedInput schema / properties / package

Added value: +{
+  "description": "Format z estimateWebsite (recommendedPackage), jeśli już wybrany",
+  "enum": [
+    "start",
+    "firmowa",
+    "marka",
+    "landing",
+    "ewizytowka",
+    "narzedzie",
+    "odoo"
+  ],
+  "type": "string"
+}

addedInput schema / properties / pages

Added value: +{
+  "description": "Łączna liczba stron, ze stroną główną (blog = 1 strona)",
+  "minimum": 1,
+  "type": "integer"
+}

removedInput schema / properties / userConsent

Removed value: -{
-  "description": "Zgoda użytkownika na przesłanie danych do właściciela serwisu",
-  "type": "boolean"
-}

changedInput schema / required

Previous value: -[
-  "userConsent"
-]New value: +[]

First observedAug 20, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces this by ruling out any send action or consent requirement, which removes a real ambiguity for a tool named 'create'. It also names the returned parts (brief, missing, next step), valuable since there is no output schema, though it doesn't say how missing data is derived or whether re-invocation overwrites prior state.

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?

Four short sentences, front-loaded with what the tool does and immediately followed by the safety caveat and the return contract. Nothing is padded, though the sentence about returns could be merged without loss.

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 no-output-schema, zero-required-parameter tool, the description covers the three things an agent needs: it is safe, it returns a brief plus a missing-data list plus a next step, and the result is forwarded verbatim. Slightly incomplete on what drives the 'missing' list and whether partial inputs are acceptable.

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% and every one of the 15 optional fields is documented in the schema, so the description carries no parameter-level information beyond the forwarding instruction. Baseline 3 applies; it correctly signals the schema's package/estimate fields should carry over from estimateWebsite but adds no format guidance itself.

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 ('Porządkuje dane zebrane w rozmowie w brief projektu') and immediately differentiates itself from the write-path siblings by saying it sends nothing and needs no consent. The agent can tell this is the non-mutating structuring step that feeds submitInquiry.

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?

Explicitly routes the agent forward: 'Wynik przekaż bez zmian jako brief do submitInquiry', which tells it this is a preparatory step in a pipeline. It does not explain when to prefer estimateWebsite first or when a brief is premature, so the ordering with the other sibling is only partially covered.

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

All jmiszewicz - wycena i zapytania o strone internetowa 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?