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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered and the description's job is lighter. The description adds real value by disclosing the returned fields (slug, name, shortName, status) and defining what each status means—context that is not in any structured field.

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?

Three tight sentences: the action and scope, the filter with its value definitions, and the return shape. The scope is front-loaded and nothing is repeated for padding.

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 zero-required-parameter read tool with no output schema, it covers action, filter semantics, and return fields—enough for an agent to call it correctly. It does not mention result size or pagination, which matters for a 'list every visual' call on a potentially large catalog.

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 100% and the enum is already typed, so the baseline is 3. The description earns an extra point by defining the domain meaning of each enum value ('live' = published on Microsoft Marketplace, etc.)—semantics the schema only names, not explains.

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 definition pairs a specific verb ('List') with a specific resource ('every visual in the SmartVisuals catalog') and names the fields returned. It implicitly distinguishes itself from find_visuals by promising an exhaustive enumeration, though it never names that sibling explicitly.

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 explains the optional filter ('Omit to return all visuals'), which gives clear usage context for the one parameter. It offers no guidance on when to prefer this over find_visuals or get_visual, so the agent must infer the distinction from the 'every visual' wording.

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