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

The description goes well beyond the annotations by disclosing the two distinct merge semantics: identifiers "replace the set" while props are "merged" — critical, since the replace behavior is what makes destructiveHint=true meaningful. It also adds per-entry independence and partial-failure reporting, which idempotentHint alone does not convey. It stops short of stating permission requirements or what happens to a board's children when parent_board_id changes.

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?

Three compact sentences, front-loaded with the mutation and batch shape, then the field list, then the outcome contract. Zero filler. The all-caps "CHANGES" is a minor stylistic wart rather than wasted space.

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 an output schema present, the response format need not be explained, and the description correctly limits itself to noting that results name updated entries and failure reasons. For a two-parameter mutation tool with a fully documented nested schema, the remaining gaps (permissions, cycle handling on parent_board_id, the item cap) are minor.

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 the schema already documents parent_board_id ("null for the top level") and identifiers ("Ids from another system"), so the baseline is 3. The description does add genuine value by clarifying replace-vs-merge for identifiers and props, but it is silent on the draft parameter and on constraints like the 100-item cap.

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?

"CHANGES boards, one or many per call" gives a specific verb plus resource and immediately states the batch shape (array of board_id + fields). It enumerates the mutable fields (name, view, parent_board_id, identifiers, props), so an agent knows the scope precisely. It never names the sibling create_boards or delete_board to contrast with, which keeps it just short of a 5.

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?

"one or many per call" and "Each is changed on its own" imply when batching is appropriate, and the failure semantics tell the agent it can send mixed batches. However, there is no explicit routing guidance such as when to use this versus create_boards, or which sibling handles card-level moves versus board nesting. Usage is implied rather than stated.

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