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

Beyond the annotations (readOnly=false, destructive=false, openWorld=false, idempotent=false), it discloses three non-obvious traits: only supplied fields are mutated, changes propagate to later image sets, and an empty fact value deletes that fact. It also states the cost is free and that the product is returned, though it omits failure behavior for invalid fact keys.

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 mutation and partial-update semantics are front-loaded in the first two sentences, followed by cost, return value, and a compact concrete example. Every clause carries information and nothing is repeated from the schema verbatim.

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 six-parameter partial-update tool with no output schema, the description covers what can be changed, how to source fact keys, removal semantics, downstream effects on image sets, cost, and the return value. An agent has enough to invoke it correctly without further discovery.

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 67% schema coverage, the description compensates by translating friendly names to schema fields (kind→category, selling points→features, scene→setting) and adding meaning the schema lacks: features are short lines printed on images, capped at five, and facts are keyed from list_products with empty-value removal semantics. This is real value beyond the JSON Schema text.

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 opens with a specific verb and resource ("Changes a product's...") and enumerates exactly which attributes can be modified: name, kind, selling points, facts, and scene. That field-level enumeration clearly separates it from create_product, delete_product, and list_products, so an agent can select it without opening the 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 establishes clear context for use: partial update ("Only the fields given change") and the dependency on keys obtained from list_products for facts. It does not explicitly state when not to use it versus create_product or move_product, but the mutation-on-existing-product framing makes the boundary obvious.

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