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

The description adds substantial behavior beyond annotations. It discloses the key surprise: 'invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list'. It explains connect links for credentials, checkout/top-up links for empty wallets, and the permission requirement: 'Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin'. No contradiction with annotations (readOnlyHint=false, openWorldHint=true is consistent with the described behavior).

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?

For a tool with 14 actions and 23 params, the length is justified — every clause carries information. However, it's a single dense wall of text with en-dash run-ons and no paragraph breaks or bullets, which hurts scannability for an agent parsing quickly. The most important info is front-loaded (marketplace, core flow), but structure could be dramatically improved with sectioning per action group.

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 extreme complexity (14 actions, 23 params, no output schema), the description is remarkably complete: it covers the full discovery→invoke flow, the not-installed invoke behavior, connect/checkout redirects, permission requirements, and the entire prompt-library subdomain. The main gap: no description of return/response shape at all — with no output schema present, an agent cannot anticipate what the tool returns for any of the 14 actions. Minor params (immediate, conversation) also go unexplained.

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 bears full burden. It compensates strongly for the most important params: the entire action enum (all 14 values explained), mcp_id, tool_id, arguments, query intent, and all prompt params (prompt_slug, prompt_vars, prompt_body, prompt_title, prompt_targets, prompt_description). However, several params remain undefined: immediate, conversation, cancel_comment, report_context, request_name, request_details, and limit get no semantic explanation despite 0% schema coverage.

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?

Exceptionally clear purpose: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It explains the core flow (search → describe → invoke), enumerates the capability requests it handles ('find an MCP that does X', 'consulta um CPF'), and contrasts with siblings (marketplace catalog vs. direct tools). The breadth is appropriate because the tool itself is a 14-action dispatcher, and the description maps every intent to its action.

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 when-to-use guidance throughout: 'prefer invoke for a single/occasional use' vs. 'Use install only to make an MCP PERMANENT in the active toolkit'; 'request_mcp asks us to build a NEW MCP when nothing fits'; 'list_tools lists what is callable right now'; 'subscribe/cancel handle per-MCP billing'. Also names the prompt-library sub-actions (search_prompts, get_prompt, publish_prompt) with distinct purposes.

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