Notifications Tool

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

With no annotations, the description carries the whole burden; it does disclose the read defaults (unread only, newest first) and that marking read is a side effect gated on the person having seen the item. It does not say whether marking read requires any authorization, whether ids are validated, or whether the call returns the notification list when mark_read is used, which is a real behavioral ambiguity for a tool that both reads and mutates.

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?

Front-loaded with the resource and its contents, then defaults, then the write behavior and the caution — every clause carries information. The telegraphic style ("mark_read marks some (by id) as read") is dense but readable and wastes nothing.

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 four-parameter tool with no annotations and no output schema, the description covers defaults and both mutation modes adequately, but leaves the return shape of a notification and the list-plus-mark interaction unspecified. An agent knows when to call it, but not exactly what it gets back.

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 100%, so the baseline is 3. The description adds loose framing ("some (by id)", "all of them", "newest first") but the schema already defines `all`, `limit`, `mark_read` and `mark_all_read` with equal or greater precision.

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?

It names a concrete resource (the person's notifications / "the bell") and enumerates what flows through it: tasks assigned, comments and mentions, morning summary, feedback answers. It also states the two modes bundled into the tool (list, plus mark_read/mark_all_read). It stops short of naming a sibling such as team_activity or my_day to contrast against.

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?

"Use it for 'what is new for me?'" gives a clear selection criterion, and "Only mark them read when the person has seen them or asks" is an explicit constraint on the mutating path. No alternative tool is named for the adjacent cases (e.g. project-wide activity), so the routing is not fully closed.

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