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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds rich behavioral context beyond this: invoke runs one-off 'without bloating the tool list,' returns connect/checkout links when credentials or payment are needed, and notes that writes require workspace owner/admin. It also clarifies the installed_in_toolkit vs installed_in_workspace flags. No contradiction with the readOnlyHint=false annotation.

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 (~250 words) but proportionate to a tool with 14 actions and 23 params. It is front-loaded with the core flow, then the critical invoke behavior, then install-vs-invoke guidance, then secondary actions, then the prompt library aside. Every sentence earns its place, though a single dense paragraph without section breaks makes it harder to scan than it could be.

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 extreme complexity (14-action enum, 23 params, no output schema), the description covers the essential ground well: core flow, auth/payment edge cases, install vs invoke distinction, permission model, and the prompt library subsystem. Gaps remain for return-value formats per action (no output schema to fall back on) and several lesser-used params (immediate, tier_slug, conversation), but the coverage is strong overall.

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% across 23 parameters, so the description must compensate. It meaningfully covers the core flow params (action, query, mcp_id, tool_id, arguments) and the prompt library params (prompt_slug, prompt_title, etc.), but leaves several undocumented — immediate, tier_slug, conversation, cancel_comment, report_context, request_details, prompt_targets, prompt_category, prompt_body — with no mention of their semantics or defaults. Partial compensation at best.

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 explicitly states the tool is 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' with a clear verb+resource framing. It enumerates the core flow (search → describe → invoke) and covers every action in the enum, leaving no ambiguity about what the tool does and how the actions relate to one another.

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 when-to-use guidance: 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT,' plus explicit edge-case handling ('If the MCP needs a credential/login, invoke returns a connect link'). It names alternatives (list_tools, request_mcp when 'nothing fits') and states the permission requirement for writes (owner/admin). This is model guidance.

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