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

Beyond annotations (readOnlyHint=false, openWorldHint=true), the description discloses key behaviors: invoke runs tools one-off without adding to the toolkit, returns connect/checkout links when credentials/payment are needed, and writes require workspace owner/admin. It also explains the installed_in_toolkit vs installed_in_workspace flags and the fact that invoke includes a hidden one-off install. This adds substantial actionable context.

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 long but every sentence adds unique, non-redundant value. It is front-loaded with the core purpose, then flows into key distinctions (invoke vs install), permission notes, and the prompt library. It could be slightly more concise, but the density is justified given the tool's complexity. The structure is logical and scannable.

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 23 parameters, no output schema, and multiple sub-actions, the description is remarkably complete. It covers the full workflow, behavioral edge cases (credentials, payment), permission model, the prompt library, and even gives examples of capability requests. It does not detail every return value, but the core outcomes are stated (e.g., describe returns full profile, invoke returns connect/checkout link). This ensures an agent can operate the tool effectively.

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 23 parameters and 0% schema description coverage, the description carries a heavy burden. It mentions the action enum implicitly via the flow (search, describe, invoke) and explains that describe returns tool id + params, pricing, auth, but it does not explain individual parameters like limit, query, immediate, tier_slug, prompt_vars, etc. Some parameters are self-evident from the schema, but many subtle ones (immediate, tier_slug, prompt_targets) remain undocumented. The description provides a conceptual layer but not parameter-level semantics.

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.ai marketplace for discovering and running MCPs/tools, and it enumerates specific actions (search, describe, invoke, install, etc.). It distinguishes itself from sibling tools by outlining the core search→describe→invoke flow and the prompt library. The verb+resource pairing is specific and 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?

It explicitly provides when-to-use guidance: 'prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT in the active toolkit', and describes alternatives like list_tools for what is callable now. It also notes permission requirements for writes (workspace owner/admin) and differentiates MCP vs prompt library usage.

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