Verify MCP Server

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint. The description adds valuable behavioral context: unknown servers return trusted=false due to lack of evidence, not proven harm. This clarifies a potential misunderstanding. No contradiction with annotations.

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?

The description is three sentences, no wasted words. The first states purpose, the second enumerates inputs, the third clarifies return behavior. Front-loaded and efficient.

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 single-parameter tool with output schema, the description covers the purpose, acceptable inputs, and a key behavioral nuance. No missing critical information; the output schema handles return structure.

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 schema only defines 'server' as a string with no additional context. The description compensates fully by listing the many accepted input types (GitHub repo/URL, npm/PyPI, display name, slug, server URL), adding critical meaning beyond the schema.

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 it provides a 'pre-connect trust verdict' for MCP servers or AI agents, which is clear. However, it does not explicitly distinguish from sibling tools like 'check_agent_trust', so the differentiation is implied but not spelled out.

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 lists acceptable input formats (GitHub, npm, etc.), which tells how to use it. But it lacks any guidance on when to use this tool versus alternatives such as 'check_agent_trust' or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.