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

Annotations already cover readOnly, idempotent, and closed-world, so safety is handled. The description extends this with the readiness lifecycle (pending | ready | failed | available | unavailable) and the requirement to wait before downstream calls, which is genuine behavioral context beyond the structured fields.

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 purpose, then the exact-check recipe, then the fallback, then the sequencing caveat. Every sentence carries procedural information, though the jargon density (SOURCE window, prepared without intent) slows comprehension slightly.

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?

An output schema exists so return values need not be explained, and the description still surfaces the exact.state enum, which helps interpret results. Combined with the annotation coverage, an agent has enough to call and use the tool correctly, with only the exact response shape left to the output schema.

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 coupling semantics the schema does not: the three filters must be sent together and anchored to the same SOURCE window as prepare_media, and the paired-omission case is a valid whole-source query rather than an error.

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 and resource: reading prepared subject tracks and behind-subject mattes for one media item. It is clearly distinguishable from read siblings like get_media_context and get_composition, though it never names an alternative tool directly.

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 explicit conditions: pass kind + startSec + endSec together for an exact readiness check using the same SOURCE window sent to prepare_media, or omit all three filters for a whole-source check when subjectTrack was prepared without intent. It also adds a sequencing rule (wait for the fact to be ready before preview_frame / score_composition).

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