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

Annotations already declare readOnly/idempotent/non-destructive, so the description correctly spends its budget elsewhere: it discloses that results are 'bounded' and paged across three separate collections, and that cards are non-authoritative while live descriptors define availability. That authoritative-vs-advisory distinction is correctness-critical context annotations cannot carry.

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?

Two dense sentences with no filler, front-loaded with the resource description and ending on the price-exclusion constraint. The first sentence is overloaded, packing the grid formula, cards, and catalog into one run-on clause, but every element earns its place.

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 10-parameter, multi-collection tool with no output schema, the description covers the three return families and the pricing caveat but omits how the four non-pagination filters narrow results and says nothing about response shape. Adequate to start, insufficient to call correctly on the first try.

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 0% across 10 parameters, so the description must carry the full burden and does not. It implies the three pagination pairs (limit/offset, card_limit/card_offset, detail_limit/detail_offset) via 'paged', but leaves kind (image/video/audio), topics, model_key, and catalog_sub entirely unexplained, forcing the agent to guess at required shapes and filters.

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 (Read) and three concrete resources: Canvas planning policy, paged model cards, and a live catalog projection of variants/modes/inputs/parameters. The scope is clear enough to act on, but it never names the overlapping siblings (aimixer_knowledge_get, aimixer_model_card, aimixer_catalog, aimixer_canvas_capabilities), so an agent must infer why this tool wins over those.

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?

"Cards guide workflow; only live descriptors define availability/parameters" gives an explicit precedence rule for interpreting results, and "Prices are excluded and must come from estimate/validate" routes the agent to a named alternative tool. It stops short of stating when to pick this over aimixer_knowledge_get or aimixer_catalog.

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