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

Even though annotations are minimal (readOnlyHint=false, destructiveHint=false), the description discloses critical behavioral details: invoke runs tools without permanently installing them; install makes MCPs permanent; credential requirements trigger connect links; payments may require wallet top-up; and search/describe flag installed_in_toolkit vs installed_in_workspace. This goes well beyond the 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 long but intentionally dense, covering an unusually complex tool with many actions, subfeatures, and caveats. It is organized logically: summary → core flow → key caveats → permission/authentication → prompt library feature. Every sentence adds unique value, though the length might challenge quick scanning.

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 tool with 23 parameters, no output schema, and weak annotations, the description is remarkably complete: it covers core actions, edge cases (connect links, checkout links), permission requirements, and a nested prompt-library feature. Some gaps remain: it doesn't list every action in the schema (e.g., 'resume', 'list_tools' is mentioned but not fully bound to action values), and it doesn't explain the response format or retry logic in more detail.

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 coverage and 23 parameters, the description does heavy lifting by explaining the 'action' parameter values (search, describe, install, uninstall, subscribe, cancel, resume, list_tools, search_prompts, get_prompt, publish_prompt) and the purpose of prompt-related parameters (prompt_body, prompt_slug, prompt_vars, prompt_tool, prompt_title, prompt_category, prompt_targets). However, many parameter meanings (e.g., conversation, request_details, report_context, immediate, tier_slug) are only implicitly covered. No parameter syntax details are provided, but the description gives enough high-level meaning for an agent to infer usage.

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, encompassing catalog search, MCP execution via invoke, installation, subscription management, and prompt library access. It uses specific verbs (search, describe, invoke, install, list_tools) and distinguishes itself from generic 'marketplace' sibling tools by explaining its unique scope.

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 gives explicit when-to-use guidance: use invoke for one-off tasks, install for permanent toolkit additions, list_tools to see callable tools, request_mcp for new MCPs, and the prompt library functions for prompt text. It also clarifies the flow for auth (connect link) and payment (checkout/top-up link) and notes that writes require owner/admin access.

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