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

Annotations are minimal (readOnlyHint=false, openWorldHint=true), so the description carries the disclosure burden and excels: it openly states invoke can run tools without install, returns connect links for missing credentials, returns checkout/top-up links for empty wallets (with a retry directive), and that writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. 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 line breaks, bullets, or section headers despite covering 14 distinct actions across two domains (MCPs and the prompt library). It lacks front-loading — the key 'invoke works without install' insight is buried mid-paragraph. Highly informative but poorly structured for agent parsing.

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 high complexity (23 params, 14-action enum, no output schema), the description is remarkably thorough: it covers the full MCP lifecycle (search, describe, invoke, install, billing via subscribe/cancel, report_bug, request_mcp) plus the prompt library, and notes installed_in_toolkit vs installed_in_workspace flags. Some return-format detail is absent given no output schema, and the density hurts extractability, but coverage is essentially complete.

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 and 23 parameters, the description carries full responsibility and explains the most important ones in context: action (all 14 enum values are covered by the workflow narrative), mcp_id, tool_id, arguments, tier_slug (pricing), and the prompt_* family (prompt_body, prompt_vars, prompt_title, prompt_description, prompt_category, prompt_targets). However, several params remain unexplained (limit, query, message, immediate, conversation, request_name, request_details, cancel_reason/cancel_comment, report_context), so it doesn't fully compensate for the coverage gap.

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 states the tool is the official MCP marketplace — the in-platform catalog of MCP/tools and the way to run them. It names specific capabilities ('find an MCP that does X', 'consulta um CPF') and lays out the core search → describe → invoke flow, which distinguishes it from sibling tools like tribunal_stj_certidao_negativa_consultar (a specific MCP tool) and toolkit_info (which lists current state).

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 strong contextual guidance: when to use invoke (one-off, works without install) vs install (permanent toolkit addition), the recommended discovery workflow, and the prompt-library path (search_prompts/get_prompt/publish_prompt) vs MCP path. It lacks explicit mentions of when NOT to use the tool or named alternatives among siblings, but the prefer-invoke-over-install recommendation is clear enough.

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