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

Annotations already declare readOnly/idempotent, but the description adds real behavior the schema cannot: it runs Milanote's own search over every board you can open, returns only the first page, and a board whose title matched comes back with no matches — a genuinely non-obvious quirk. It also discloses the sort default and the presence of 'matches' and 'path' in results.

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?

Purpose and scope are front-loaded, then result shape, then sorting, then the pagination caveat with the escape hatch. The Search-icon analogy is a short, useful mental model rather than filler, and no sentence is redundant.

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 output schema, the description carries the burden of describing return values and does it well: result is a board with 'matches' cards and a 'path', plus a note that only the first page comes back. An agent has everything needed to call it and to know when to escalate to get_board.

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%, so the baseline is 3; the description earns above that by explaining what 'sort' actually means in practice ('when you last viewed the board, or last modified') rather than just restating the enum. 'query' is only glossed as text search, which is already covered by 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?

States a specific verb and resource ('Find boards and cards by text') plus the scope ('across your boards'), which separates it from list_boards, list_recent_boards and get_board. It also immediately defines the result unit ('Each result is a board'), so the agent knows what a hit actually is.

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?

Makes clear this is the text-search entry point and gives an explicit follow-up route: 'use get_board on a result to read all its cards'. It does not explicitly contrast with list_boards or list_recent_boards for browsing-style needs, so the when-not-to-use side is only implied.

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