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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description reveals critical behaviors: invoke runs one-off without adding to toolkit, install makes permanent, writes require workspace owner/admin, and invoke may return connect or checkout links for auth/payment. It also explains that search/describe flag installed vs workspace status, which goes well beyond structured metadata.

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 well-structured, front-loading the core purpose and flow. It covers many aspects in a single cohesive paragraph without excessive repetition, though some trimming could improve scannability. Given the tool's complexity, the length is justified and each sentence adds 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?

For a tool with 14 actions, 23 parameters, and no output schema, the description provides remarkably complete context. It explains the core workflows, the one-off vs permanent distinction, auth/payment handling, billing via subscribe/cancel, the prompt library, and permission requirements. It effectively fills gaps left by the absent output schema and parameter descriptions, making it highly usable for an 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?

With 0% schema description coverage, the description must compensate. It explains the key 'action' enum values and how they map to flows, and mentions specific parameters like mcp_id, tool_id, arguments, and prompt-related fields. However, it does not systematically cover all 23 parameters, leaving some (e.g., limit, query, message) to be inferred from context or default values, so it does not fully substitute for missing schema descriptions.

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 official mcp.ai marketplace' and explains its core function: cataloging and running MCPs/tools. It distinguishes itself from siblings by detailing its unique actions (search, describe, invoke, install) and the prompt library, which are not covered by other tools like authenticate or show_version.

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 each action: 'prefer invoke for a single/occasional use' and 'use install only to make an MCP PERMANENT'. It outlines the core flow (search → describe → invoke), mentions when to use subscribe/cancel, report_bug, and request_mcp, and clarifies that search/describe flag installation status, giving clear when-to-use and when-not-to-use directions.

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