Convert raw HTML you already have into clean Markdown (no fetching).
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": {
"html": "<html>"
},
"name": "convert_raw"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| key | No | ||
| html | Yes | raw HTML to convert |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose one meaningful trait: no network fetching occurs. Beyond that it is silent on what 'clean Markdown' means (which tags are stripped, how tables/scripts are handled), whether failures on malformed HTML are raised, and why a `key` parameter exists — likely auth or quota, which is never mentioned.
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?
A single front-loaded sentence with the core action first and the disambiguating constraint immediately after. Zero wasted words.
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 two-parameter tool it covers the essentials: input source and output type (clean Markdown), so no output schema is needed. It remains incomplete on the unexplained `key` parameter and on error/conversion edge-case behavior, which an agent would need before calling with unfamiliar input.
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 only 50%: `html` is documented in the schema, but `key` has no description anywhere. The description adds nothing about either parameter — no format notes for the HTML input, no indication of what `key` is or whether it is required for auth/quota. A gap this size warranted compensation and received none.
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 (convert HTML into Markdown) and adds the scoping qualifier 'raw HTML you already have (no fetching)', which distinguishes it from the sibling `convert` that presumably retrieves content. An agent can pick between them without opening either schema.
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?
The parenthetical 'no fetching' tells the agent the precondition for using this tool: content must already be in hand. It stops short of naming the `convert` sibling as the alternative for the fetch case, so routing is implied rather than explicit.
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.