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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds substantial behavioral context: the operation defaults to a cost preview, lands as a new current revision, has automatic fallback for background-removal provider failures, has retry limits (two per failed job per session), and has no daily removal retry lockout. It also discloses the paid nature (60 credits) and the dryRun behavior. No contradiction with annotations.

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 description is dense and front-loaded with the most important constraint (LEGACY ONLY) and the cost warning. It covers many operational details in a compact block. It is long, but every sentence carries operational information an agent needs; the structure is a single block of imperative guidance rather than a clean list, which slightly hurts scannability.

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 paid, mutating, async operation with no output schema, the description is remarkably complete: it covers cost, dryRun, pre-checks, fallback behavior, retry limits, idempotency, and the return shape ({ jobId }). The only minor gap is that it doesn't describe the full output of the real (dryRun:false) call beyond jobId, but the description explicitly says 'Returns { jobId }', which is sufficient for polling.

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 description coverage is 100%, so the schema already documents all four parameters. The description adds value by explaining the dryRun default and the confirmation flow, and by clarifying that assetId must be a legacy texture asset, not a Material. It doesn't add much beyond the schema for iterationId or idempotencyKey, but the schema already covers those well.

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 and resource ('Make an old texture tile seamless') and clearly distinguishes this from siblings by declaring 'LEGACY ONLY' and noting that new Brushable Materials reject the operation. It also names the related get_asset check, so an agent can tell this apart from convert_texture_to_material or reprocess_asset.

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?

The description gives explicit when-to-use guidance: check get_asset first, use the free seamMetric.pass verdict, and do not spend on a cell that already passes. It also explains the dryRun flow, when to re-call with dryRun:false, and when to avoid spending. This is far beyond a minimal usage note.

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