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

Beyond annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description adds rich behavioral context: invoke returns connect links for credential needs, checkout/top-up links for empty wallets, and instructs to retry after user action. It also discloses that writes require workspace owner/admin and explains installed_in_toolkit vs installed_in_workspace flags. This goes far beyond what annotations provide.

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 a dense single paragraph but logically organized: core purpose → core flow → key invoke behavior → install vs invoke distinction → prompt library → permissions. Every sentence adds value, but the length could be better structured with bullet points or section breaks for improved scannability given the complexity.

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?

Given the tool's complexity (23 parameters, no output schema), the description covers most essential flows and edge cases (authentication, billing, permissions, installed vs one-off), and even explains return values for some actions (invoke links, publish_prompt shareable URL). However, some actions like 'resume' are not explained, and several parameters remain undocumented, so completeness is strong but not exhaustive.

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?

With 0% schema description coverage, the description partially compensates by explaining action enum values (search, describe, invoke, install, etc.), and the roles of mcp_id/tool_id} in the workflow. It also touches on prompt-related parameters like prompt_vars. However, many parameters remain unexplained (immediate, conversation, request_name, report_context, prompt_targets, etc.), leaving gaps in semantic understanding.

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 clearly defines the tool as the official mcp.ai marketplace catalog and execution engine, using specific verbs like search, describe, invoke, and install. It explicitly distinguishes itself from sibling tools like authenticate and connect by focusing on discovery and running of MCPs, and it also covers the separate prompt library capability.

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 an explicit decision tree: use search to discover MCPs, describe to get full profiles, invoke for one-off runs (even when not installed), install only for permanent toolkit additions, and list_tools for currently callable tools. It explicitly states 'prefer invoke for a single/occasional use' and names alternatives, leaving no ambiguity about when to use each action.

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