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

Annotations are sparse (readOnlyHint=false, openWorldHint=true), so the description carries a heavy burden and delivers: it discloses that invoke works even when the MCP isn't installed, returns connect/checkout links and asks the user to open them before retrying, and states that writes require workspace owner/admin. It also explains side effects like 'one-off install behind invoke' and permanent-toolkit changes from install, going well beyond annotation-provided info.

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 every sentence earns its place, covering the core flow, key edge cases (not installed, paid/wallet empty), permission requirements, and the prompt library. It is front-loaded with the main purpose and action flow. However, the lack of any bullet points or paragraph breaks makes it harder to scan; a structured format would earn a 5.

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 high complexity (14 actions, no output schema, no required params), the description is remarkably complete: it explains the search-describe-invoke flow, install vs one-off invoke, auth/credential handling, billing top-up behavior, permissions for writes, list_tools for current callables, the prompt library, and error-recovery retry pattern. It prepares the agent to handle most realistic scenarios without needing additional external documentation.

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?

Schema coverage is 0% with 23 parameters, but the description compensates partially by explaining the meaning of key parameters: action's enum values (search vs describe vs invoke vs install), tool_id as the selected tool from describe, and arguments as parameters to that tool. It also describes the prompt-related actions (search_prompts, get_prompt, publish_prompt) and their purpose. However, it does not detail many peripheral params like tier_slug, immediate, cancel_comment, report_context, or prompt_vars, so it isn't a full substitute for schema-level semantics.

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 states a clear purpose: 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It enumerates specific sub-actions (search, describe, invoke, install, list_tools, subscribe, etc.) and distinguishes them from one another, making it unmistakable what this tool does and how it differs from siblings.

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: 'Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile... invoke RUNS that tool.' It also states exclusions and preferences: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use,' and clarifies when to use request_mcp ('asks us to build a NEW MCP when nothing fits'). This is exemplary usage guidance.

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