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

With no annotations, the description carries the full burden and does a lot: it discloses that images are downscaled ~1024px, capped at 8, delivered at most once per project, that videos come as labeled contact sheets, and that include_details surfaces prompt/model/settings/inputs across any project of the brand. Gaps remain around error behavior and what happens if caps are exceeded.

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, then bullets map cleanly to parameters, ending with the sequencing constraint. Dense but nearly every clause carries operational information; a couple of phrasings ('AT MOST ONCE per project') are terse enough to risk misreading.

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 5-param tool with no output schema and thin schema documentation, the description explains what comes back (visible image copies, motion contact sheets, generation metadata) and how to behave. Missing only edge-case behavior such as exceeding the 8-image / 20-id caps or failure modes.

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 only 20% (only project_id is documented), yet the description fully compensates: it defines artifact_ids as emero ids OR external https image URLs, gives defaults and semantics for images (downscaled copy, up to 8, once per project), include_details (exact prompt, model, settings, roles, project), and force (only after compaction). This is meaning well beyond the bare boolean/array schema.

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 ('Look at assets yourself') plus a crucial scope distinction ('never shown to the user') that separates it from a user-facing view tool. It doesn't name the sibling `view` explicitly, so the agent must infer the contrast, which keeps it short of a 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?

Gives explicit conditions and sequencing: 'Call it in its own step — after check_generation's result has arrived, not alongside it', 'pass force:true ONLY after your context was compacted', and two concrete purposes (review MOTION, rebuild a past prompt / debug repeated fixes). The when-not condition on `force` is exactly the kind of exclusion that prevents misuse.

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