review_notes

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

With no annotations, the description has to carry behavior, and it does most of the work: it discloses the default status filter (open), what each note contains (1-based frames, the fixed tag vocabulary, user text, per-frame pixel bbox and pixel data in sprite coordinates), and the composition of the returned image (previous / marked / next frame). It never explicitly states the operation is read-only or describes volume/pagination limits for large projects, 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?

The purpose is front-loaded in the first line and the enumeration of note contents is dense but purposeful, with no filler sentences. The text is a single long run-on block that would read better split by parameter or return value, but nothing 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?

For a three-parameter read tool with no output schema, the description supplies the return shape (frames, tags, text, bboxes, pixels, composed images) and the default filtering, which is close to complete. The gaps are the undocumented `pictures` flag and no statement that the call is non-mutating or that fixing requires the separate resolve_note/resolve flow.

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 0%, so the description must document all three parameters, and it only covers two: `path` (omitted → all sprites under allowed folders) and `status` (open | resolved | all, default open). The `pictures` boolean is never explained — the sentence about what a note's picture contains hints at image output but doesn't tell an agent what setting `pictures: false` suppresses.

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 description opens with a concrete statement of the resource: user-marked issues in Studio Live (wrong frames, painted pixels, tags, text). That is enough for an agent to tell it apart from pixel-inspection siblings like read_pixels or find_glitches. The phrasing is slightly indirect — it describes what the notes contain rather than saying plainly 'returns review notes' — so it falls short of a clean verb+resource statement.

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: 'Without `path`, every sprite with notes under the allowed folders' conveys the broad-vs-targeted selection, and 'Fix, then resolve_note' points at the natural follow-up. There is no explicit when-to-use/when-not-to-use framing against siblings such as find_glitches or lint, which also surface animation problems.

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