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

Annotations already declare destructive=true, openWorld=true, idempotent=false, but the description adds substantial context beyond them: it may call writing providers and is not always zero cost, it requires the plan:create scope, Soclo verifies the private conversation and funding before new work, and it warns against re-dispatching when the outcome is unknown. These are exactly the operational details an agent needs before invoking a costly, non-idempotent mutation.

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 in the first clause and every subsequent clause earns its place (cost, no filming, alternative route, auth requirement, failure handling). It is dense and semicolon-chained rather than cleanly sectioned, which slightly hurts scannability, but there is no wasted content.

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 destructive, costly, non-idempotent mutation with no output schema, the description covers everything: preconditions (auth scope, verified conversation/funding), cost behavior, the confirm gate, the routing alternative for imported plans, and the recovery path for unknown outcomes. An agent has enough to invoke it correctly or route elsewhere.

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% and every parameter already carries a description in the schema, including the confirm gate and the clientRequestId reuse instruction. The description largely restates confirm:true and the original UUID clientRequestId, so it adds little semantic value beyond the structured fields. Baseline 3 is appropriate.

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 (prepares) and resource (an existing Soclo-app-authored ready revision) and scopes it precisely to plans authored by the app using their retained conversation and original native terms. It actively distinguishes itself from three siblings: it never films (soclo_video_make), imported host plans must go to soclo_quote, and unknown outcomes go to soclo_video_preparation_status.

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 when-to-use (Soclo-app-authored ready revision with retained conversation), when-not-to-use (imported host plans cannot use this writing route; use soclo_quote instead), and a failure path (if outcome unknown, do not dispatch again; read soclo_video_preparation_status). Nothing 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.