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

The description adds substantial context beyond the annotations (readOnlyHint=false, openWorldHint=true). It discloses that invoke runs one-off without installing or bloating the tool list, that auth needs return a connect link, that empty wallets return a checkout/top-up link with a retry instruction, and that writes require workspace owner/admin. It also flags installed_in_toolkit vs installed_in_workspace status. No contradiction with 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 a single dense wall of text with no paragraph breaks or bullet lists, despite its considerable length (covering 14 actions plus billing, auth, and the prompt library). The purpose and core flow are appropriately front-loaded, and every sentence carries real information, but the lack of structural organization makes it hard to parse and locate specific action semantics quickly.

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 very high complexity (14 actions, 23 params, no output schema, 0% schema coverage), the description covers the main behavioral flows well — the search→describe→invoke pipeline, one-off execution, auth/payment edge cases, and permission requirements. But it omits per-action return values, does not explain many parameters (limit, query, immediate, tier_slug, conversation), and does not detail cancel/subscribe semantics beyond naming them. Adequate but with clear gaps for a tool this complex.

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 description coverage is 0%, so the description carries full burden for parameter meaning. It does explain the central parameters functionally — action (via the core flow), mcp_id and tool_id ('invoke RUNS that tool... with its id + params'), arguments, and the prompt_* fields. However, roughly half the 23 parameters (limit, query, immediate, tier_slug, conversation, cancel_reason, request_name, prompt_targets, etc.) receive no semantic explanation in the text, leaving those under-documented.

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 opening line, 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' gives a specific verb+resource plus scope, clearly identifying this as the discovery-and-execution hub for MCPs. It also distinguishes the prompt-library sub-domain. However, the tool is a 14-action dispatcher spanning search, install, billing, and prompts, so the single 'purpose' is somewhat diffuse across multiple sub-purposes.

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?

Explicit guidance is abundant: the 'Core flow: action=search → describe → invoke' pipeline explains when each action is appropriate. It explicitly contrasts invoke ('prefer invoke for a single/occasional use') with install ('only to make an MCP PERMANENT'), and clarifies that list_tools reports what is callable right now. It also separates the prompt-library actions (search_prompts/get_prompt/publish_prompt) from MCP management.

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