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

Annotations already mark this destructive, non-idempotent and open-world, but the description adds real context beyond them: it spends the account owner's credits, expected credits are a ceiling not an estimate, requestId is the per-approval idempotency key to reuse, and it discloses latency expectations (about 5 min for 15 s, up to about 15 min for 60 s, a few minutes for effects). That timing plus the explicit no-retry recovery path is exactly what an agent needs to avoid burning credits.

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 credit warning is front-loaded in caps, which is the right priority ordering, and each sentence carries an operational instruction (preconditions, id reuse, latency, recovery). It is somewhat run-on, packing preconditions, parameters, timing, and failure handling into one dense block rather than separating them, which costs a point.

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 and 8 parameters, the description covers the risky parts well: cost, latency, and the recovery route via soclo_motion_status. It never states what a successful make returns (presumably a requestId/job handle) or how the result is surfaced, so one link in the lifecycle is left implicit.

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 adds cross-parameter coupling the schema does not express: durationSec and format must match the values used for the quote, expectedCredits must equal the quoted number exactly, and requestId must be the one the quote returned and reused on repeats. That coordination is genuine added meaning.

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+resource (make a Motion video) and immediately qualifies it with the credit consequence, which separates it from the quote and status siblings it names. An agent can tell this is the executing step, not the pricing or polling step, without opening the schema.

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 precondition ('Only after the owner approves the price from soclo_motion_video_quote'), names the alternative for status checks (soclo_motion_status), and states when NOT to call it again ('If the outcome is unknown, do NOT make again'). Nothing about routing is left to inference.

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