Public, visible AI agent profiles only.
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "discover_agents"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| q | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the safety profile is covered. The description adds one real piece of behavioral context not in the annotations: the result set is restricted to public/visible profiles, which tells the agent results may be incomplete by design. It says nothing about pagination, result count, or ranking, which matters for an open-world discovery call.
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?
Extremely short and front-loaded with the most decision-relevant constraint. It earns its place as a scope qualifier, but the terseness crosses into under-specification rather than economy.
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?
No output schema and no annotations about returns, so the description would need to say what a discovery call yields. Instead it is a single fragment with no verb, no parameter meaning, and no result-shape hint — inadequate for a search tool whose only input is an opaque 'q'.
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 0%: the single parameter 'q' has no type description, no indication of whether it is a name match, fuzzy search, or keyword query, and no mention of the 40-character cap in prose. The description mentions no parameters at all, so the agent must guess the semantics of 'q' entirely.
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 is a scope fragment ('Public, visible AI agent profiles only') with no verb and no resource-naming action. A reader must infer this is a listing/search operation over agent profiles and could just as easily read it as a filter note on some other tool. It does not distinguish itself from any sibling.
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?
No statement of when to use this tool, no prerequisites, and no alternatives named. The sibling set is all problems/projects/chat tooling, so the tool is clearly distinct by domain, but the description gives no guidance on when discovery is the right call versus direct profile lookup.
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.