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

Annotations already indicate readOnlyHint=false and destructiveHint=false, but the description adds critical behavioral detail: invoke runs tools without installing them, install/uninstall/subscribe/cancel require workspace owner/admin, and invoke may trigger a one-off install behind the scenes. It also explains the return behavior (connect/checkout links). This exceeds 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 dense but not bloated; every sentence adds information about a different action or edge case. It is front-loaded with the core purpose and flow. However, it is a single wall-of-text paragraph without bullet points or structural aids, which hurts scannability for a 14-action tool.

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 (14 actions, 23 params, no output schema), the description covers the main flows comprehensively: search→describe→invoke, install persistence, billing/auth recovery, prompt library, permission model, and sibling distinctions. Minor gaps exist (resume action, immediate parameter, cancel_reason semantics), but the overall context is sufficient for an agent to operate effectively.

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 23 parameters and 0% schema description coverage, the description must compensate. It explains the action parameter's role and the relationship between describe (returns tool_id) and invoke (uses tool_id), and implies prompt_vars for get_prompt. However, many parameters (limit, immediate, tier_slug, conversation, request_name, prompt_* fields) are not described, leaving the agent to infer from names and defaults. This is a partial compensation, not full.

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 identifies the tool as the mcp.ai marketplace, a catalog and execution engine for MCPs/tools, and distinguishes it from sibling tools like authenticate/connect. It enumerates the core flow (search → describe → invoke) and secondary actions, so the agent understands the tool's sphere.

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 provides explicit guidance on when to use invoke vs install ('prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT'), and explains list_tools, report_bug, request_mcp alternatives. It also gives conditional behavior for auth/billing (connect link, checkout link), making the decision tree actionable.

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