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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses the non-obvious core behavior: it opens nothing by itself, returns procedural instructions, and requires a follow-up browser automation step. It also explains the underlying reason — Milanote has no public API or official MCP server — which an agent needs to understand why the tool is instruction-only rather than data-returning.

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 key disclosure (returns steps, opens nothing, use browser tools) is present but buried in a long clause, and 'from ChatGPT, Claude or any AI agent' plus the awkward 'Milanote's official API: Milanote has no public API' phrasing add noise. The most decision-relevant fact — that no board data is returned — should lead the description.

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?

With no parameters and no output schema, the description carries the whole burden, and it does explain the instruction-returning nature and the browser follow-up. However, it never states what the response actually contains (a board list? a procedure?) or how the agent should locate the boards afterward, leaving the primary ambiguity of the tool unresolved.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-parameter tool applies. No parameter-related omissions exist.

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 name and title say 'List boards', but the description reveals the tool actually 'Returns how to do it in Milanote step by step (screens, buttons, fields)' rather than the boards themselves — a meaningful gap between label and behavior. It also never distinguishes itself from the very similar sibling names list_boards, list_recent_boards, and search_boards, leaving an agent unsure which lister to pick.

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 gives a concrete next step: after calling this, 'do it with the cotlet_browser_* tools in the user's Milanote Cloud Browser', which tells an agent exactly how to continue the workflow. It stops short of stating when to prefer this over the sibling list_boards/search_boards tools or any preconditions.

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