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

Annotations already establish readOnly/idempotent/non-destructive, but the description adds real behavioral context beyond them: oldest-first ordering by creation time and ID, default/max page size, cursor-following rule, and the important caveat that this is a live collection rather than a snapshot of concurrent edits. Auth/permission behavior is still unstated, keeping it short of 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?

The definition is dense but every sentence carries distinct information: scope, return contents, ordering, pagination, cursor rules, and the retry guidance. The front-loaded scope statement is good, though the packed clauses around cursor/activityId interaction read as slightly run-on.

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?

With an output schema present the description need not explain return shapes, and stateful details like pagination, ordering, and live-collection behavior are covered. Combined with annotations carrying the safety profile, an agent has everything needed to call this correctly.

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%, so the baseline is 3, but the description adds semantics the schema does not: activityId 'returns zero or one exact matching item and cannot use a cursor,' plus the rule to follow each non-null nextCursor with unchanged targets and restart after edits. The limit parameter is only restated, not enriched.

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 and resource with scope: 'Read saved actions on this Site/Topic recommendation without changing them,' and clarifies it returns saved details plus activity IDs and references. The contrast with list_recommendation_notes is implied by the 'actions' resource but never made explicit, so sibling differentiation is only partial.

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?

Gives an explicit usage condition: 'Use this read after an uncertain write before retrying creation; creation may duplicate,' which tells the agent exactly when this read is valuable. It also covers the activityId filtering case vs. cursor pagination, though it never names a sibling alternative outright.

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