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

Provides rich behavioral detail far beyond the sparse annotations (readOnlyHint: false, openWorldHint: true): '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 discloses conditional auth flows ('if the MCP needs a credential/login, invoke returns a connect link'), payment edge cases ('if it is paid and the wallet is empty, invoke returns a checkout/top-up link'), and permission requirements for writes. 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?

A ~290-word wall of text in a single unbroken paragraph with no lists, headers, or bolding. While the first sentence is strong and front-loaded, the mid-paragraph 'KEY:' and 'Writes (...)' parentheticals add parse burden. Mixed-language content ('pontualmente') and quoted strings further reduce scannability. The content is valuable but desperately needs bullets or sentence-per-line structure to match the adjacent rubric examples.

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 14 actions, 23 parameters, no output schema, and no parameter descriptions, the coverage is strong: the full lifecycle (search→describe→invoke), billing/subscription behavior, the prompt library subsystem, and operator permission model are all explained. Gaps exist (resume action semantics, error conditions, idempotency), but given the complexity, the description is nearly exhaustive in scope.

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 coverage across 23 parameters, the description correctly bears the meaning burden and covers much ground: it explains action enum values (search, describe, install, invoke, list_tools, subscribe, cancel, report_bug, request_mcp, search_prompts, get_prompt, publish_prompt), the tool_id→invoke relationship, and the prompt library parameters (prompt_slug, prompt_body, prompt_vars). However, several parameters (immediate, resume, conversation, cancel_reason) are never mentioned, leaving gaps in an already-parameter-heavy tool.

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 opens with 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' immediately establishing a specific verb+resource. It names concrete capability requests ('find an MCP that does X', 'consulta um CPF') and lays out the core search→describe→invoke flow. It clearly differentiates from all siblings (authenticate, connect, report_bug, show_version, toolkit_info, tribunal_trt20_processo_consultar), none of which overlap with marketplace/catalog/execution functionality.

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?

Excellent explicit when/when-not guidance: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use' and 'list_tools lists what is callable right now.' It even explains the search discovery path, the fallback behavior (connect link, checkout link), and distinguishes MCPs from the PROMPT LIBRARY ('which is about ready-made prompt TEXT rather than MCPs'), giving a full decision tree.

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