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

Annotations declare idempotentHint=true and destructiveHint=true; the description earns its keep by explaining exactly why: it replaces the slide's background image, determinism holds for 'the same recipe and `seed`', and a stale `expectedVersion` fails with DECK_CONFLICT before any work. It also discloses side effects not in the annotations — text recolouring for contrast unless `adaptInk:false`, and objects rendering BEHIND the copy.

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 highest-value facts (what it draws, that it is free and fast) and every clause carries information. It is one dense ~250-word paragraph though, and the long material/pattern enumerations would read far better as a bulleted list or grouped sentence.

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 9-parameter tool with nested objects, no output schema and thin schema descriptions, it covers the side effects, version precondition, paid-overwrite confirmation and determinism. It never mentions the return value or the role of locale/projectId/accountHandle, but those are minor relative to the recipe guidance it does provide.

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 only 44%, but the description compensates heavily: it defines the recipe shape (base, ≤4 layers, light, ≤8 objects, grain/vignette/scrim), the five `base` variants and their shader/material enumerations, palette-slot colour values, object placement via x/y or `on`, and `seed` re-roll semantics. The only untouched parameters are locale, projectId and accountHandle.

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?

Opens with a specific verb+resource ('Draw a procedural background on a deck's slides') and immediately distinguishes itself from the model-based sibling: 'by code, not by a model: FREE, no credits, about a second.' An agent can tell this apart from antix_generate_deck_slide_images or antix_clear_slide_background 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?

It sets the condition for dropping existing paid art ('needs `confirmDropPaid:true` after the user agrees') and states 'Omit `slideIds` for every slide', which is real invocation guidance. It stops short of naming alternatives (e.g. when to prefer model-generated art via antix_generate_deck_slide_images instead), so an exclusion rule is left implicit.

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