Generate ULIDs: 26-character, lexicographically sortable, timestamp-prefixed identifiers. Pure CPU, instant.
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"count": "<count>"
},
"name": "ulid"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | How many ULIDs |
Changes observed during successful MCP inspections.
Input schema / properties / countAdded value: +{
+ "description": "How many ULIDs",
+ "type": "integer"
+}Input schema / requiredAdded value: +[
+ "count"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full behavioral burden. It does say 'Pure CPU, instant', which usefully rules out network calls or async waits, but it leaves the important traits unstated: whether results are random/unique, what case/encoding the identifiers use (Crockford base32, typically uppercase), and whether repeated calls can collide. For a generator with zero annotation coverage, that is a meaningful gap.
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 short, front-loaded sentences with no filler; the identifying characteristics come first and the operational note ('Pure CPU, instant') trails. Nothing could be cut without losing information.
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?
A one-parameter generator with no output schema means the description should describe the return value, and it doesn't say whether the agent gets a single string, an array, or newline-separated values when count > 1. That omission is the main reason this is only adequate for such a simple 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?
Only one parameter, and the schema already documents it at 100% coverage ('How many ULIDs'). The description adds no constraints the schema lacks, such as an upper bound on count or whether bulk calls return a delimited list. Baseline 3 applies when the schema does the heavy lifting.
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 ("Generate ULIDs") and goes further by defining the output's properties: 26 characters, lexicographically sortable, timestamp-prefixed. That definition implicitly separates it from uuid/nanoid/generate_uuid siblings, but it never names them for contrast.
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?
There is no explicit when-to-use or when-not-to-use guidance, and no mention of the obvious alternatives (uuid, nanoid, generate_uuid) that sit in the same toolset. The 'lexicographically sortable' trait implies the reason to pick this over a random UUID, but the agent has to infer it.
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.