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

Annotations are sparse (readOnlyHint: false, destructiveHint: false), so the description carries the burden — and it delivers. It discloses critical runtime behaviors: invoke runs one-off without installing ('runs the tool pontualmente'), returns connect links for auth, checkout links for empty wallets, openWorldHint=true aligns with the arbitrary capability requests stated. No contradiction with annotations, and substantial value is added beyond what the annotations state.

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 ~300-word single unbroken paragraph with no bullets, line breaks, or examples. Mixed-language usage ('consulta um CPF', 'pontualmente') creates ambiguity. Dense semantically, but the structural choices force multiple re-reads to extract the flow. The information deserves 4s, but the presentation badly needs formatting.

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 exceptional complexity (23 params, no required fields, 14-action dispatcher, 3 sub-flows), the description covers capability discovery, one-off invocation, permanence semantics, billing/auth edge cases, permission requirements, and prompt library features. Very few gaps exist in content — mostly gaps in navigation/structure.

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 coverage is 0% with 23 parameters and only 2 enums, putting a heavy burden on the description. The description does excellent work explaining the 'action' enum values (search→describe→invoke flow, search_prompts/get_prompt/publish_prompt), which is the semantic core. However, 16+ parameters (conversation, cancel_reason, prompt_targets, request_details, arguments, etc.) receive zero explanation, and the mcp_id/tool_id relationship is only implied, not stated.

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 opener 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them' clearly establishes identity and scope. It defines coverage boundaries ('Covers capability requests like...') which aids sibling differentiation, though the purpose is inherently diffuse across 14 actions and 3 sub-flows, and no single verb captures it.

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?

Provides explicit when-to-use logic: 'Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use.' Also covers edge cases (auth connect links, payment top-up then retry) and permission requirements ('Writes... require workspace owner/admin'). Loses a point by not explicitly naming alternative tools or a decision tree for sibling differentiation.

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