suggest_motion

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description does disclose that it writes artifacts (a playground per suggestion and a map) plus that anything not renderable is listed in approximations, so the write behavior is not hidden. It adds genuinely new constraints (http/https only; local or private addresses permitted only when url itself is local) and return-path details (map_path, preview_url). The gap is that it never says where files land or whether it can overwrite an existing playground for the same element, which is what a destructiveHint should forewarn about.

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 is front-loaded in sentence one, then the batch flow, personalization gates, approximation disclosure, next-step handoff, single-element variant, and URL constraint follow in a coherent order. It is long and a few clauses are run-on, but nearly every sentence carries operational information rather than restating the title.

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 seven-parameter tool with no output schema, the description covers inputs, both operating modes, the artifacts produced, the follow-up call, and the URL restriction that would otherwise cause hard failures. An agent has enough to select the mode, build valid arguments, and continue the workflow without further probing.

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, but the description adds cross-parameter meaning the schema does not: selector 'sets max to 1 and builds no map', trigger is conditional on selector and is derived from what the designer said about timing, and profile/project must be passed together or omitted together. Viewport and max are left to the schema, which is acceptable given full coverage.

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 first sentence delivers a specific verb and resource ('Find the places on a page where motion would help, and build a playground for each') and enumerates the six moment types it detects. It also implicitly distinguishes itself from create_motion_playground and open_motion_playground by ending in an explicit handoff to the latter, so an agent can route 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?

Two distinct modes are spelled out with selecting conditions: the batch/audit mode, which requires passing profile and project so suggestions follow the designer's notes, and the single-element mode triggered when 'the designer names one element in chat', which requires a selector found in the code or from get_grabbed_elements. It also states the next step (call open_motion_playground with map_path) and the exclusion ('a none-instant or no motion note returns no suggestions').

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