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

Annotations only carry the generic destructive/openWorld/non-readOnly profile; the description adds the concrete cost model (spends credits, tier pricing), the side effect (saved to Soclo Library, returns libraryAssetId/resultUrl, never raw bytes), the async contract (202 image_result_pending, re-send same request id), and the reconciliation path (soclo_image_recover). The claim that an exact replay is free sits in mild tension with idempotentHint=false, but the description frames it as request-id-keyed dedupe while warning 'Never retry an unknown outcome automatically', so it does not contradict the annotation.

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 cost and side effect, then the preconditions, then the async/recovery contract — a sensible priority order. It is dense and clause-heavy (the clientRequestId sentence packs reconciliation, pending handling, and retry prohibition into one run-on), but almost every sentence carries operational information rather than filler.

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?

No output schema exists, yet the description still names the return shape (libraryAssetId, resultUrl, no raw bytes) and the pending-status outcome. Combined with the pricing/approval prerequisites, reference-locator sourcing, and recovery tooling, an agent has everything needed to call this correctly and to handle failure.

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, and much of the description (imageUrls as reviewed private locators, premium default, owner-exempt 0 credits) restates schema text. It still adds value by sequencing the parameters as a workflow ('quote first, then pass expectedCredits, pricingVersion and ownerApprovedPrice:true') and by tying clientRequestId to recovery and replay behavior, which the schema documents only per-field.

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 ('makes one new GPT Image picture from your scene prompt') and immediately bounds the scope ('without Soclo AI planning', 'Does not attach to a plan or publish'). It explicitly carves itself away from the sibling edit/background-removal/upscale tools and from soclo_image_plan, so an agent can route 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?

Gives an explicit precondition chain: 'Quote first with soclo_image_quote, then pass expectedCredits ... and ownerApprovedPrice:true after the owner approves the price.' It names the alternatives that must be used instead ('Photo edits, background removal and upscaling use their own tools') and the prerequisite tools for references (soclo_photo_reference_prepare, soclo_brand_photo_reference).

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