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

Goes well beyond the readOnly/idempotent annotations: it discloses the post-edit settling behavior (waits a few seconds, never returns the pre-edit composition), the meaning of an error and of editRunning, layer-key instability across edits, and that no footage bytes are returned. These are non-obvious traits that materially change how an agent should call and retry.

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 return payload, then behavioral caveats, with the prerequisite placed last; every sentence carries information. It is a dense single block that would read better split into short labeled statements, but there is no filler.

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 no output schema, the description carries the full burden and does so: it enumerates the returned structure, names readAt and the revision field for freshness checks, and covers the retry/error semantics. Nothing needed to call it correctly is missing.

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?

The single deviceId parameter is fully documented in the schema, including its provenance from aftereffects_list_connections. The description only restates that provenance as an ordered call, so it adds little beyond structured data — baseline 3 applies when schema coverage is 100%.

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?

States a specific verb (read) and resource (the composition shared by your After Effects panel) and enumerates exactly what comes back: settings, layers with keys, in/out frames, transforms and expressions, project items, output templates, render queue, plus a revision. That inventory also implicitly separates it from the Premiere sibling (premiere_read_timeline) and from the edit/status tools.

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?

Gives an explicit prerequisite (first call aftereffects_list_connections to obtain deviceId) and explicit re-invocation rules: read again after an edit, read again on error, and re-read after done because layer keys shift. This is when/when-again guidance an agent can act on without inference.

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