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

Adds real context beyond the annotations: it returns a card_id, the text is plain with line breaks becoming paragraphs, the free-plan 100-card limit applies, editors see the card but nobody is notified, and the undo path is trashing in Milanote. One gap: annotations mark destructiveHint=true while the description frames the action as trivially reversible via trash — it doesn't reconcile that, nor describe what happens when the card limit is hit.

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?

Front-loads the purpose and packs useful caveats into five tight sentences. Minor waste: the opening fragment ('Note card with plain text, added to a board's Unsorted panel') is immediately restated by the following sentence and could be dropped.

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 two-parameter create tool with no output schema, the description carries everything an agent needs: where the card lands, the card_id return value, formatting semantics, plan limits, notification behavior, and how to undo. No material gaps for correct invocation.

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 coverage is 100% and both parameters are documented in the schema, so the baseline is 3. The description's plain-text/Markdown note largely repeats the schema's 'Each line becomes a paragraph', and it adds nothing about the board_id format beyond what the schema already says.

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?

States a specific verb and resource ('Adds one note card') plus placement ('on top of the board's Unsorted panel'), which separates it cleanly from add_column, add_link, add_todo_list and edit_note. Nothing about the core action is ambiguous.

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?

Usage is implied rather than stated: it's clear you use this for plain-text note cards, and the 'Markdown is not converted' line hints that formatted content belongs elsewhere. But it never names an alternative ('for tasks use add_todo_list, for URLs use add_link') or states when not to use it.

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