Search the Laso Finance agent docs (SKILL.md and the full API reference). Returns the most relevant sections. Use this for anything the tool descriptions don't answer: auth flows, funding, fees, webhooks, error handling.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search terms, e.g. fund managed wallet, or: gift card fees. |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -{
- "properties": {
- "note": {
- "description": "Where to read the full docs when nothing matched.",
- "type": "string"
- },
- "results": {
- "description": "Best-matching doc sections, most relevant first.",
- "items": {
- "properties": {
- "content": {
- "description": "Section text, truncated to 2500 characters.",
- "type": "string"
- },
- "heading": {
- "description": "Section heading.",
- "type": "string"
- },
- "source": {
- "description": "Document the section came from.",
- "type": "string"
- }
- },
- "type": "object"
- },
- "type": "array"
- }
- },
- "type": "object"
-}New value: +nullDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses that the tool searches a specific doc set and returns the most relevant sections, which is sufficient to understand it as a read-only lookup. It does not detail pagination or result formatting, but for a docs search tool this is a minor 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 sentences with no wasted words. The core function and scope are front-loaded, followed by concrete usage guidance and example topics. Every sentence earns its place and the description is immediately scannable for an agent.
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 one-parameter search tool with no output schema, the description covers what is needed: what is searched, what is returned, and when to use it. It also gives practical examples of the kinds of questions it answers, making it complete in the context of the large sibling tool set.
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 input schema has one parameter with 100% description coverage, so the baseline is 3. The description itself adds no additional parameter-level nuance beyond naming the search behavior and context; the schema already defines 'query' with an example. This meets the minimum viable bar but does not elevate it.
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 states a specific verb ('Search'), a clear resource ('Laso Finance agent docs (SKILL.md and the full API reference)'), and the expected output ('most relevant sections'). It clearly distinguishes itself from the many sibling tools by being the documentation search fallback rather than a banking, card, or payment operation.
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 description explicitly tells the agent when to use this tool: 'Use this for anything the tool descriptions don't answer' and lists concrete example topics (auth flows, funding, fees, webhooks, error handling). This provides a clear routing rule and implicitly excludes using it for questions already answered by other tool descriptions.
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.