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

Annotations only carry idempotentHint/destructiveHint, so the description does the heavy lifting and does it well: atomic all-or-nothing billing, ~15-30s wall time, the exact return fields (batchId, tasks[], totalCredits, creditsRemaining, estimatedSeconds), and a polling cadence via antix_check_batch. Limits (10 items, 4 variations, 40 images) and the reference-resolution priority chain are disclosed.

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 core action, then structured with bold headers and bullets so an agent can skim to the relevant section. Slightly inflated by persuasive framing ('Why this over N sequential...') and duplicated limit/speed claims, but almost every sentence carries operational information.

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 13-parameter tool with no output schema, the description compensates by enumerating return fields, polling behavior, billing semantics, and hard limits. Remaining shortfall: `referenceImages`, `idempotencyKey` retry semantics, and the projectId/sessionId asset-routing behavior are left to the schema (or undocumented), which matters for a paid batch operation.

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?

With only 31% schema coverage, the description usefully explains the `items` array (1-10 entries, `prompt` required, per-item overrides), the top-level shared-param inheritance rule, and the five-step reference resolution order. The notable gap is `referenceImages` (plural, up to 10) which appears only in the schema and is never reconciled with the singular `referenceImage` priority chain.

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 (submit N image generations in parallel) and immediately distinguishes itself from the sequential sibling by contrasting with 'N sequential generate_image calls'. An agent can route between this, antix_generate_image, and antix_check_batch without opening a 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 trigger ('use this whenever the user asks for multiple different scenes / poses / variations at once') with a worked example, names the alternative it replaces, and states the boundary condition ('for >10 different prompts, send multiple sequential batches'). When-to-use and when-to-split are both covered.

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