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

The annotations only say readOnlyHint=false and destructiveHint=false, but the description reveals substantial behavioral details: invoke works without installing, may return a login/connect link or a checkout link, and writes (install/uninstall/subscribe/cancel) require workspace owner/admin. It also discloses side effects like 'without bloating the tool list' and the prompt library's anonymous-access behavior.

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 information-dense with zero filler — every sentence contributes — but the presentation is a single massive wall of text with minimal structural breaks. It front-loads the key concept well but sacrifices scannability, which is a real cost when an agent needs to quickly parse a decision.

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 15-action, 23-parameter function with no output schema and no parameter descriptions, the description covers the full complexity: the discovery-to-execution flow, the install-vs-invoke tradeoff, credential and payment edge cases, role-based write permissions, and the entire prompt library sub-system. It covers the hard parts that neither the schema nor annotations provide.

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, and it does for the most critical parameter (action) and the endpoints that matter (mcp_id, tool_id, prompt_slug). However, roughly a third of the 23 params (tier_slug, immediate, conversation, prompt_body, prompt_title, report_context, etc.) are never explicitly explained. It's a strong-but-not-complete compensation, so 4 is appropriate.

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 what this is — 'the in-platform catalog of every MCP/tool, AND the way to run them' — and establishes the core flow: search discovers MCPs → describe returns profiles → invoke runs tools. It is specific about verbs and resources, and distinguishes against siblings (report_bug, request_mcp) with explicit contrasts like 'report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits.'

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?

Gives explicit guidance on when to use what: 'prefer invoke for a single/occasional use,' 'Use install only to make an MCP PERMANENT,' and 'list_tools lists what is callable right now.' It also names the exact alternative (request_mcp for new MCPs, report_bug for feedback), which is precisely the when/when-not/alternatives pattern the rubric rewards.

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