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

Beyond the annotations, the description discloses a crucial cost guarantee (quoting debits no credits and saves nothing - the recipe/settings aren't persisted, even though readOnlyHint=false because the returned quote/hash is itself retained), the required auth scope (read:accounts), and the presentation obligation to show the owner per-video Create Ad price plus planning charge, limits, caps and approvals. It even enumerates the return contents, which is valuable since no output schema exists.

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 core purpose is front-loaded and every sentence carries information (guarantees, prerequisites, display instructions, data retention, auth). It is dense and slightly run-on with mid-sentence procedural imperatives ('Show the owner...'), but there is no filler and no repetition.

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 quote tool with no output schema and rich annotations, the description is nearly complete: purpose, prerequisites, what to surface to the owner, the hash to retain, and the auth scope are all covered. The remaining gap is that the directionScope parameter and the internal shape of patch are left unexplained.

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 0%, so the description carries the full burden; it explains expectedUpdatedAt well (source, null-for-absent) and gives conceptual meaning to patch (optional proposed changes). However, it says nothing about the opaque directionScope object or the clientRequestId, and gives no insight into the deep nested patch structure (domains, guardrails, toggles). It compensates for only part of a 4-param, heavily nested 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?

The description states a specific verb (preview/get) and resource (an app quote for the saved recipe plus the effective video spending ceiling) and bounds the scope to the recipe with an optional patch. It clearly distinguishes this from soclo_autopilot_read (source of the expectedUpdatedAt token) and soclo_autopilot_enable (downstream consumer of the returned hash). An agent can identify the tool's job without opening any 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?

It gives explicit preconditions and sequencing: pass expectedUpdatedAt from soclo_autopilot_read (null when absent), and saved explicit settings must exist first. It also names the follow-up (keep approvedTermsHash for soclo_autopilot_enable), making the when-to-use and position-in-flow unambiguous.

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