Compare two texts and return token overlap and similarity scores. 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": {
"a": "<a>"
},
"name": "word_similarity"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | First text | |
| b | No | Second text |
Changes observed during successful MCP inspections.
Input schema / properties / aAdded value: +{
+ "description": "First text",
+ "type": "string"
+}Input schema / properties / bAdded value: +{
+ "description": "Second text",
+ "type": "string"
+}Input schema / requiredAdded value: +[
+ "a"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations supplied, the description carries the full behavioral burden. It usefully discloses that the tool is pure CPU and instant (no network call), and mentions token overlap, but it never states what the similarity score represents (scale, algorithm, direction) or what happens if the optional second text is omitted.
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 sentences, front-loaded with the core action and followed by a useful performance note; nothing is wasted. Brevity here is close to under-specification rather than bloat, but the phrasing itself is clean.
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 two-string comparison tool with no output schema, the description is adequate but leaves real gaps: the score semantics and the required-versus-optional asymmetry between "a" and "b" are unexplained. An agent could invoke it, but could not predict or interpret the result confidently.
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 both parameters ("a" and "b") are documented as first/second text in the schema itself; the baseline of 3 applies. The description adds no meaning beyond that, and notably does not explain that "b" is optional while "a" is required, which is the one semantic detail the schema leaves implicit.
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 sentence "Compare text similarity scores" essentially restates the tool name word_similarity and adds little specificity. It does not name the inputs (two texts) or say what the scores mean, so an agent distinguishes it from siblings like levenshtein or text_diff only by guessing.
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 statement of when to use this tool versus alternatives such as levenshtein, text_diff, diff, or compare. No exclusions, no preconditions, and no scenario guidance are provided.
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.