List memory

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lowered, yet the description still adds value beyond them: 'free' communicates no credit cost, 'the same Memory the web app shows' tells the agent the data source is consistent with the UI, and 'these shape every future ad' conveys downstream impact. It does not describe return format or ordering, keeping it from a 5.

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 tightly packed sentences with the resource front-loaded, followed by scope clarification and the read-only/free qualifier. The parenthetical is dense but earns its place by defining the resource contents; minor redundancy between the title and opening verb keeps it from a 5.

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 simple, annotation-backed read tool with fully documented parameters and no output schema, the description supplies what memory represents and its downstream use, which is enough to call it correctly. It could still note ordering or default behavior, but nothing critical is missing.

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%, with both limit (default 50, max 200) and category buckets fully documented in the schema, so the baseline is 3. The description's mention of the brand/audience/taste/do-don't buckets loosely echoes the category filter but adds no format, syntax, or semantics beyond what the schema already provides.

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 (List) and resource (durable facts & preferences in this workspace's Memory), and enriches it with the domain content (brand, audience, taste, do/don't rules). However, it never differentiates the action from the closely related siblings remember, forget, and tidy_memory that operate on the same resource, so it stops short of the 5 tier.

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?

The 'these shape every future ad' framing implies you inspect memory before generating ad content, and 'Read-only, free' signals it is safe to call liberally. But there is no explicit when-to-use versus remember/forget guidance and no stated exclusions, leaving usage to inference.

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