find_capabilityUp to 25 real MCP servers for a need, with connection info and measured reliability, best first. Use to compare options yourself. Example: {"need":"weather forecast","limit":10}
| Name | Required | Description | Default |
|---|---|---|---|
| need | Yes | What you need to do | |
| limit | No | 1-25, default 8 | |
| detail | No | compact (default) or full | compact |
| remote_only | No | true = callable over HTTPS only |
Changes observed during successful MCP inspections.
Input schema / properties / detail / descriptionPrevious value: -"compact (default, fewer tokens) or full (measurement methods, badges, sample inputs)"New value: +"compact (default) or full"Input schema / properties / limit / descriptionPrevious value: -"How many options to return (1-25, default 8)"New value: +"1-25, default 8"Input schema / properties / remote_only / descriptionPrevious value: -"true = only tools callable over HTTPS, nothing to install"New value: +"true = callable over HTTPS only"Input schema / properties / detailAdded value: +{
+ "default": "compact",
+ "description": "compact (default, fewer tokens) or full (measurement methods, badges, sample inputs)",
+ "enum": [
+ "compact",
+ "full"
+ ],
+ "type": "string"
+}Input schema / properties / limit / descriptionAdded value: +"How many options to return (1-25, default 8)"Input schema / properties / remote_only / descriptionAdded value: +"true = only tools callable over HTTPS, nothing to install"Input schema / properties / need / descriptionPrevious value: -"What you need to do, e.g. 'extract text from a scanned PDF'"New value: +"What you need to do"Input schema / properties / remote_only / descriptionRemoved value: -"Only servers callable over HTTPS (no local install)"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior: result cap of 25 and best-first ordering with reliability scores attached. It does not say what happens with zero matches or how 'detail' affects the payload size, which leaves gaps.
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 plus a compact example; the core value (real servers, connection info, reliability, best first) is front-loaded and every element is relevant. Slight loss for the example sitting on its own line rather than integrated.
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?
With four parameters and no output schema, the description should convey the shape of a result entry. It names the fields at a high level (connection info, reliability) but not enough for an agent to decide between detail=compact and detail=full, nor what a no-result response looks like.
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%, so every parameter (need, limit, detail, remote_only) is already documented in the schema, including the enum and the 1–25 bound. The description's example shows need and limit in use but adds no semantics for detail or remote_only beyond what the schema provides, so the baseline 3 fits.
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+resource: returns up to 25 real MCP servers matching a need, each with connection info and measured reliability, ordered best first. This is clear, but the description does not distinguish it from nearby siblings such as check_reliability or faceabot_more_tools, so it stops one level short of full clarity.
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 phrase 'Use to compare options yourself' implies it is a discovery/browsing tool as opposed to something like get_need or offer_capability, but no explicit when/when-not conditions or named alternatives are given. The guidance is inferable rather than stated.
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.