Read a preset's stored content and references, or a pool's storage defaults

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 well: it declares read-only, states the 'Needs bridge 0.22.0' requirement, documents the defaults assumed for absent layers (width/trans 100, accel/decel 0, 60 BPM, phase 0), and explains that embedded sources are followed recursively with validity flags. It adds genuine behavioral context about missing data and dependency resolution rather than restating the schema.

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 content is front-loaded with 'Read-only.' and the version requirement is helpfully placed at the end, but the bulk is one very long run-on sentence enumerating return fields. It is dense and hard to parse, so size and readability suffer even though little is strictly 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?

There is no output schema, so the description must explain what is returned — and it does cover both modes and the recursive dependency inspection thoroughly. Given the complexity of the return structure, the coverage is strong, though the cramped prose slightly limits how completely an agent can absorb it.

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 baseline is 3, but the description goes further by explaining what each parameter actually retrieves: 'preset' returns per-fixture/attribute stored modes, values, steps, phaser layers, fade/delay and dependencies, while 'pool' returns the pool's default mode, input filter and store preferences. This semantic mapping of parameter-to-output exceeds the bare schema descriptions.

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 title and description state a specific verb+resource (read a preset's stored content/references, or a pool's storage defaults) and lay out two distinct modes keyed by parameter. An agent can tell this is a read of preset/pool storage rather than a store or listing. It stops short of explicitly naming which sibling to use when, so it earns a solid 4 rather than 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?

The description implies usage via the 'preset:' vs 'pool:' parameter modes and the 'Read-only' framing, but never states when to reach for this tool over alternatives such as gma3_pool, gma3_get_object, or gma3_cue_contents. There are no exclusions or prerequisites beyond the bridge version. Adequate but leaves routing to inference.

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