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

Annotations already mark read-only, idempotent, and non-destructive. Description adds context about being provider-verified and operator-curated, and explicitly states it does not execute a remote business tool. No contradiction; description enriches without repeating 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?

Four concise sentences: purpose, output, usage timing, and non-execution note. Front-loaded with the key action, no fluff or redundancy. Each sentence adds distinct value.

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?

Covers purpose, output content (remote read-only tools with descriptions, schemas, annotations), usage timing, and a constraint (does not execute). No output schema exists, but the description sufficiently explains what will be returned, making it complete for the agent.

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 single parameter id_or_slug is fully described in the schema (100% coverage) with details about being a UUID or slug from search_tools. The description does not add further meaning beyond what's already in the schema, so baseline 3 applies.

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?

Clearly states the action (live-inspect a server) and specifies the target (active, provider-verified, operator-curated public MCP server from the 404.directory catalog). It distinguishes from siblings like search_tools and invoke_registered_tool by focusing on inspection and explicitly noting it does not execute a remote tool.

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?

Provides explicit when-to-use guidance: 'Use after search_tools and before the first invoke_registered_tool call, or whenever arguments may have changed.' Also clarifies it does not execute a remote business tool, which prevents misuse. No alternatives listed but sequencing is clear.

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