notification_log

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

With no annotations, the description carries the burden and does disclose non-obvious behavior: newest-first ordering, inclusion of already-dismissed items by default, and that each row carries the turn it arrived on. It does not explicitly state the operation is read-only or describe result size/pagination beyond limit, so a small gap remains.

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 purpose and the newest-first scope are front-loaded, and every sentence carries information. It is slightly discursive with the em-dash asides ("which is what the screen is for"), but no sentence is wasted.

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 2-parameter read tool with no annotations and no output schema, the description covers both parameters, the row shape, and ordering. It could say more about what a row contains beyond turn, but nothing needed to invoke it correctly 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 0% — the schema gives only titles and defaults — so the description must compensate, and it does: limit is the newest N with default 40, and include_dismissed=false keeps only notifications still showing, which also clarifies the true default.

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?

Names a specific resource (the notification log) and states its exact scope: every notification still held, newest first, dismissed ones included. It is immediately distinguishable from the sibling turn_digest, which it names and contrasts.

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 routes the agent: turn_digest only carries what the panel currently shows, so anything read once and dismissed is otherwise gone — use this tool for that history. The selecting condition and the alternative are both stated, leaving nothing to inference.

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