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

The description discloses many important behavioral details beyond the annotations: invoke runs a tool even when the MCP is NOT installed (one-off, without bloating the tool list), invoke returns a connect link when credentials are needed, invoke returns a checkout/top-up link if paid wallet is empty, the one-off install behind invoke requires owner/admin, search/describe flag installed_in_toolkit vs installed_in_workspace, and the separate prompt library (search_prompts/get_prompt/publish_prompt with shareable login-free links). It does not heavily disclose destructive/write risks, but the annotations (openWorldHint=true, destructiveHint=false) already cover some of the trust profile. Minor gap: it could explicitly state the mutating effects of install/uninstall on the toolkit beyond 'permanent', but the existing detail is strong. Note: readOnlyHint is false, so the description's mention of install/uninstall/subscribe as writes is consistent with 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 text is dense and substantial (almost half a page), but most sentences carry unique information about the tool's actions and flows. It is loosely structured in a single paragraph; breaking it into sections (Core flow / invoke behavior / install behavior / billing & admin / prompt library) would improve scanability. The information density is high and not bloated, but the lack of structure reduces readability for an agent doing quick decision-making.

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 25 parameters, no output schema, and many sub-actions (search/describe/install/invoke/subscribe/prompt-library), the description provides an unusually thorough map: the search→describe→invoke flow, the not-installed behavior, the auth/payment edge cases, the admin-required write actions, and the distinction between the MCP catalog and the prompt library. This nearly compensates for the lack of output schema and the 0% parameter schema coverage. It leaves some minor gaps (e.g., exact output/bucket_details per action, list_tools outcome), but for such a complex tool, it is very strong.

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% in the schema, but the description compensates with rich context about the core parameters: action (enum), mcp_id, tool_id, arguments (JSON string), and the prompt parameters (prompt_slug, prompt_body, prompt_vars, etc.). It explains what each major action expects (search uses query, invoke uses tool_id+arguments), and describes the response-driven flows (connect link, checkout link) that inform how arguments should be constructed. It does not explain every one of the 23 parameters (e.g., cancel_reason/cancel_comment, report_context, request_details are not individually described), but the overall coverage is much higher than 0%. Given 23 parameters and 0% schema coverage, the description is doing a substantial job.

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 provides a rich, specific explanation of what the marketplace tool does: it's the in-platform catalog of MCPs/tools and the way to run them. It clearly lists the core flow (search → describe → invoke) and enumerates each action verb with its distinct purpose (install, subscribe, list_tools, etc.), which distinguishes it well from sibling tools. It even mentions capability requests like "find an MCP that does X" and "consulta um CPF", giving a concrete sense of 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 guidance on when to use each action: use invoke for single/occasional use (even when the MCP is not installed), use install only to make an MCP permanent, use list_tools for what's callable now, subscribe/cancel for per-MCP billing, report_bug for feedback, request_mcp for new MCPs. It also states the core flow (action=search discovers → describe returns full profile → invoke RUNS) and notes that writes require workspace owner/admin. This is far more than a typical description.

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