arrange_objects

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

With no annotations, the description carries the full burden and does so substantively: locked objects are skipped by align/distribute and reported in `skipped_locked`, distribute with fewer than 3 errors instead of silently doing nothing, group requires 2+ and returns `group`, and the stacking actions mutate `z` visible via describe_board detail "full". It never states permissions, reversibility, or limits, which keeps it below a 5.

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-loaded with the operation list and compressed into a few dense sentences with no filler. The telegraphic fragments ('group (2+ objects, returns `group`), ungroup, lock, unlock.') are efficient but cost some readability.

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 16-action tool with no output schema and no annotations, the description covers preconditions, error conditions and two return fields (`skipped_locked`, `group`). It still omits the general response shape for align/stack actions and any mention of partial-success behavior, so it is strong but not complete.

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 75%, so most parameters are already documented and the baseline sits at 3. The description's real contribution is explaining the meaning of the `action` enum values (align vs distribute vs stack vs group semantics), which goes beyond the bare enum names but is not organized parameter-by-parameter.

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?

Names a specific set of operations (align, distribute, stack, group, lock) on a specific resource and enumerates the action families, so an agent can distinguish this from move_objects, update_object or format_text without opening the schema.

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?

Explicit preconditions are given per action family: align_* needs at least 2 unlocked objects, distribute_* needs at least 3 with equal gaps between the outermost, otherwise an error. It does not, however, name a sibling as the alternative for plain repositioning (move_objects) or say when not to use this tool.

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