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

Annotations only indicate non-readonly, open-world, non-idempotent, non-destructive. The description adds rich behavioral context: invoke runs one-off without installing, returns a connect link when credentials are needed, returns a checkout/top-up link when wallet is empty (then retry), and notes that writes require workspace owner/admin. It also clarifies that search/describe flag installed status and that prompt library is separate from MCPs. 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?

The description is long (≈300 words) but every sentence earns its place. It is structured with a clear opening definition, a core-flow breakdown, a 'KEY' highlight for the most important nuance, and a separate prompt-library section. For a tool with 14 actions and 23 params, this is appropriately dense and front-loaded.

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 complexity (14 actions, no output schema, no param descriptions), the description covers the main workflows and edge cases (auth, payment, administrator rights). However, it omits some details: the 'resume' action is not mentioned, and parameters like 'immediate', 'tier_slug', 'conversation', and 'cancel_reason' are not explained. It is still remarkably complete for such a broad tool.

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 has 23 params with 0% description coverage, so the description carries the burden. It explains the meaning of key parameters: 'action' values (search, describe, invoke, install, etc.), 'tool_id' (picked after describe returns the profile), 'prompt_vars' (fills {{variables}}), and 'mcp_id' (identifies an MCP). However, it does not cover all params (limit, immediate, tier_slug, cancel_reason, etc.), so it is not fully comprehensive but adds significant meaning beyond the schema.

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's dual purpose: it is 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It explicitly covers capability requests and differentiates from siblings like 'list_tools' (which only lists callable tools) and 'toolkit_info' (which is not mentioned but implied as different). The verb+resource 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?

The description provides explicit usage guidance: it explains the core flow (search → describe → invoke), distinguishes 'invoke' from 'install' with clear recommendations ('prefer invoke for a single/occasional use'), and names alternatives like 'list_tools' for currently callable tools. It also details when to use prompt-library actions (search_prompts, get_prompt, publish_prompt). This is textbook when-to-use guidance.

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