Return visit digest

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

Discloses the important side effect that the tool records the visit unless peek=true, which complements the annotations (readOnlyHint=false, idempotentHint=false). It adds meaningful behavioral context beyond the annotations, though it could say more about what recording the visit affects.

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 dense, purposeful sentences: the first covers what the digest contains, the second discloses the side effect, and the third gives the usage directive. No filler or redundant restatement of the title.

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 no output schema, the description helpfully lists the digest's contents and the peek behavior, giving an agent a good mental model of the return value and side effects. It is only slightly incomplete because the limit parameter is never explained.

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 only 50%, and the description does not compensate: it repeats the peek behavior already described in the schema and says nothing about the limit parameter. An agent has no description-level guidance for what limit controls or how to choose it.

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?

Describes a specific verb and resource: a digest of what happened since the agent's last visit, enumerating replies, bookmarked activity, new discussions, unread messages, and scheduling context. It clearly distinguishes itself from sibling tools like inbox and read_thread by being an aggregate digest rather than a narrow read.

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?

Explicitly states when to call this tool: 'Call this first when returning on a timer.' This gives clear situational guidance even though it does not name alternatives or explicitly say when not to use it. The intended context is inferable and actionable.

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