Listuje publiczne czcionki i nici dostępne w kreatorze. Zwraca id jako odpowiednio font_id i thread_id, nazwę, podgląd jako pełny URL oraz gotowy markdown obrazu; nici zawierają także color_hex w formacie #RRGGBB. Narzędzie nie przyjmuje parametrów.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | Tylko przy isError: { code, message, ... } | |
| fonts | No | ||
| threads | No |
Changes observed during successful MCP inspections.
Output schema / properties / error / properties / detailsAdded value: +{
+ "description": "Powody odrzucenia kolorów (invalid_input z get_creator_link)",
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "allowed_option_ids": {
+ "description": "Aktywne option_id typu slotu; wybierz jedno z nich",
+ "items": {
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "type": "array"
+ },
+ "asset_type_id": {
+ "anyOf": [
+ {
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ]
+ },
+ "field": {
+ "description": "Np. slots[0].option_id",
+ "type": "string"
+ },
+ "given": {
+ "description": "Podany option_id",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "message": {
+ "type": "string"
+ },
+ "reason": {
+ "enum": [
+ "unknown_option",
+ "inactive",
+ "type_mismatch",
+ "slot_out_of_range",
+ "no_color_choice"
+ ],
+ "type": "string"
+ },
+ "slot_position": {
+ "description": "Pozycja slotu 1-based",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ }
+ },
+ "required": [
+ "field",
+ "slot_position",
+ "asset_type_id",
+ "reason",
+ "given",
+ "allowed_option_ids",
+ "message"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / error / properties / hintAdded value: +{
+ "description": "Wskazówka naprawy (invalid_input), np. lista nieznanych tagów",
+ "type": "string"
+}Output schema / properties / error / properties / causeAdded value: +{
+ "pattern": "^(timeout|http_\\d{3}|matomo_error|invalid_response|not_configured|matomo_method_unavailable)$",
+ "type": "string"
+}Output schema / properties / error / properties / code / enumPrevious value: -[
- "invalid_input",
- "not_found",
- "shop_unavailable"
-]New value: +[
+ "invalid_input",
+ "not_found",
+ "shop_unavailable",
+ "analytics_unavailable"
+]Output schema / properties / error / properties / retry_after_seconds / descriptionPrevious value: -"Po ilu sekundach ponowić żądanie (shop_unavailable)"New value: +"Po ilu sekundach ponowić żądanie (niedostępność źródła)"Output schema / properties / error / properties / statusAdded value: +{
+ "description": "Status błędu analityki; report_unavailable oznacza brak raportu/konfiguracji",
+ "enum": [
+ "report_unavailable",
+ "error"
+ ],
+ "type": "string"
+}Output schema / properties / fonts / items / properties / preview_image_urlRemoved value: -{
- "anyOf": [
- {
- "format": "uri",
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
-}Output schema / properties / fonts / items / properties / preview_markdown / descriptionAdded value: +"Gotowy markdown obrazu podglądu ; null gdy brak podglądu"Output schema / properties / fonts / items / requiredPrevious value: -[
- "id",
- "name",
- "preview_image_url",
- "preview_markdown"
-]New value: +[
+ "id",
+ "name",
+ "preview_markdown"
+]Output schema / properties / threads / items / properties / preview_image_urlRemoved value: -{
- "anyOf": [
- {
- "format": "uri",
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
-}Output schema / properties / threads / items / properties / preview_markdown / descriptionAdded value: +"Gotowy markdown obrazu podglądu ; null gdy brak podglądu"Output schema / properties / threads / items / requiredPrevious value: -[
- "id",
- "name",
- "color_hex",
- "preview_image_url",
- "preview_markdown"
-]New value: +[
+ "id",
+ "name",
+ "color_hex",
+ "preview_markdown"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly=true, idempotent=true, non-destructive and closed-world, so the safety burden is carried. The description adds real behavioral context beyond them: the returned keys (font_id vs thread_id), preview URLs, ready-to-use image markdown, and the #RRGGBB format of color_hex, plus the fact that no input is required.
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?
Three compact sentences, front-loaded with the action and resource, then the return shape, then the no-parameters note. Slightly redundant to enumerate return fields when an output schema exists, but nothing is wasted.
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 annotations, an output schema, and no inputs, this description is close to self-sufficient: it names the data source scope, the identifier keys and the value formats. Only ordering/volume of the returned list is unstated, which is minor for a fixed catalog call.
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?
The tool has zero parameters, which sets the baseline at 4. The description explicitly confirms 'the tool takes no parameters', removing any doubt, and adds nothing misleading.
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 (list) and precise resource (public fonts and threads available in the creator), so the agent knows exactly what comes back. It does not differentiate from the closest sibling, list_colors, which also returns creator palette data, so an agent must infer the boundary.
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 reader infers you call it to obtain font/thread identifiers before using them elsewhere. There is no explicit when-to-use, when-not-to-use, or pointer to the sibling list_colors for the color-only case.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.