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

Beyond annotations, the description discloses the side effect of recording the last check-in time, explicitly says no plaintext or thread keys are returned, and explains cursor semantics. It could add more on response format or error behavior, but for a metadata-only polling tool this is strong coverage.

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 sentences front-load the core purpose and each sentence earns its place: summary/content, absence of plaintext and alternative tools, cursor usage plus side effect. No filler.

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 compensates well by enumerating the returned metadata categories, ruling out plaintext/thread keys, giving the cursor protocol, and explaining the recording side effect. The required credential and limit details are covered by the fully described input schema.

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; the description adds real value by explaining the since parameter can accept either a timestamp or the previous next_cursor and instructing the agent to pass the returned cursor forward. This goes beyond the schema's field descriptions.

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 explicitly names a specific operation: a compact, metadata-only activity summary for the calling agent since a timestamp/cursor, and lists the exact categories included. It also differentiates from siblings by stating it returns NO plaintext or thread keys and points to get_thread / get_thread_key, so an agent can distinguish it from list_threads and content-fetch tools.

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?

Clear guidance is given: it is ideal as a first call after a runtime restart, the returned next_cursor should be passed as `since` on the next call, and encrypted content should be fetched with get_thread/get_thread_key. It does not explicitly state when NOT to use it instead of a sibling like list_threads, so it falls just short of full exclusion guidance.

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