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

The description discloses substantial behavioral aspects beyond the annotations: it explains that invoke works even without installation, that it returns connect/checkout links under specific conditions, that install adds tools permanently, and that certain actions are restricted by role. It also covers the prompt library's separate behavior (publish returns a shareable link). The annotations (readOnlyHint:false, openWorldHint:true) are consistent with the description; no contradictions. This is richly transparent.

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 paragraph that packs in many concepts (core flow, install vs invoke, auth/payment handling, permissions, prompt library). While information-dense, it lacks structural organization (no bullets, headings, or bolded terms) and may overwhelm the agent. Every sentence adds value, but the sheer length (around 200 words) makes it harder to parse quickly. It could be split into sections or bullet points for better scannability, earning a middle score.

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 tool's complexity (23 parameters, no output schema, no per-parameter documentation), the description is remarkably complete. It covers the end-to-end flow, conditional behaviors (auth, payment, permissions), the distinction between invoke and install, and the prompt library functionality. It also notes how to handle edge cases like missing credentials or empty wallet, and clarifies the role of list_tools, report_bug, and request_mcp. The description leaves little ambiguity about what the tool can do and how it behaves.

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 must compensate. It explains the key parameters indirectly through the action flow: query, mcp_id, tool_id, arguments, immediate, tier_slug, and the prompt_* fields are all referenced in context (e.g., 'invoke RUNS that tool' implies tool_id and arguments). However, some parameters like limit, message, conversation, and cancel_reason are not individually explained, leaving ambiguity for those. Still, given the 23 parameters, the description covers the most critical ones sufficiently, though not exhaustively.

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 identifies the tool as the official mcp.ai marketplace, covering both discovery and execution of MCPs/tools. It enumerates concrete capabilities (search, describe, invoke, install, prompt library) and explicitly distinguishes itself from sibling tools by stating it is the in-platform catalog and the way to run them. The action enum further clarifies the specific operations, making the purpose unambiguous.

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 explicit guidance on when to use each action: it explains the core flow (search → describe → invoke), highlights the key distinction between invoke (one-off, no installation) and install (permanent), and notes when to prefer invoke over install. It also specifies requirements like authentication (returns connect link), payment (returns checkout link), and permission levels (writes require workspace owner/admin). This goes beyond mere context to active decision-making guidance.

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