count_sms_partsCount SMS parts
Count GSM-7/UCS-2 segments for a message body and estimate cost without sending. Polish diacritics force UCS-2 (70 chars/part). Call this before send_sms.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | SMS body to measure. Example: "Przypominamy o wizycie jutro o 10:00." |
| Name | Required | Description | Default |
|---|---|---|---|
| hint | No | ||
| parts | Yes | ||
| length | Yes | ||
| encoding | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / text / descriptionPrevious value: -"Treść SMS"New value: +"SMS body to measure. Example: \"Przypominamy o wizycie jutro o 10:00.\""Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "encoding": {
+ "enum": [
+ "gsm7",
+ "ucs2"
+ ],
+ "type": "string"
+ },
+ "hint": {
+ "type": "string"
+ },
+ "length": {
+ "type": "number"
+ },
+ "parts": {
+ "type": "number"
+ }
+ },
+ "required": [
+ "encoding",
+ "parts",
+ "length"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is known. The description adds valuable context that Polish diacritics force UCS-2 and the 70-char limit, which is beyond annotations. It also implies a cost estimate without sending, which is helpful.
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 description is concise, but the title is in Polish, which may cause confusion for non-Polish agents. The English description is front-loaded with the purpose, and the additional details are relevant. Slightly minor issue with title language.
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 simple 1-parameter tool with output schema and annotations that provide safety, the description covers usage context, key behavioral details, and parameter implications. It doesn't specify the exact return format, but output schema is present, so not needed. Missing explicit alternative comparison, but not critical.
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% with a clear example, so the schema already documents the text parameter well. The description adds meaning by explaining the measurement logic (GSM-7/UCS-2) and the impact of Polish diacritics, which goes beyond the schema and helps the agent use the parameter correctly.
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 clearly states the verb 'Count' and the resource 'SMS parts', specifying it measures GSM-7/UCS-2 segments and estimates cost. It distinguishes itself from siblings like send_sms by explicitly stating it works 'without sending'.
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?
It says to call before send_sms, providing a clear usage context. However, it does not explicitly mention when not to use it or name alternatives, though the sibling list makes send_sms the obvious alternative for sending.
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.