Read Capture

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

Goes well beyond the annotations: discloses the 1000-event retention cap, the dropped counter when events are evicted, the ok=false failure mode versus a misleading empty list, and an explicit prompt-injection warning that page-sourced event text is data, not instructions. The clear semantics ('only the events returned are removed, so a capped read loses nothing') is the kind of side-effect detail annotations cannot express; note the mild tension with destructiveHint=false/idempotentHint=true, but the description resolves it by stating the exact scope of removal.

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?

Five sentences, each carrying distinct payload (purpose/order, retention limit, failure mode, injection safety, clear semantics), with the core purpose front-loaded and no filler or restatement of the name.

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 carries the burden of return semantics and mostly succeeds — ordering, eviction/cap behavior, dropped reporting, and the ok=false shape. The only gap is the per-event object shape (fields beyond 'text'), which the agent must infer.

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 real meaning for `clear` beyond the schema's terse wording — it clarifies that only the returned window is removed and that a capped read therefore loses nothing. It does not add much for max/kind/tab_id, which is acceptable since those are fully documented in the schema.

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?

Opens with a specific verb+resource ('Return what capture_start recorded on a tab') and immediately scopes it with ordering ('oldest first'). It clearly positions itself as the read side of the capture_start pair among siblings, so an agent can tell it apart from console_messages, network_requests, or get_page_content without opening the schema.

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 clear context for invocation (it reads what a running recorder captured) and an explicit failure condition ('no recorder is running on the current page'), which tells the agent when not to expect data. However, it never routes between alternatives like console_messages/network_requests or says when the capture pipeline is preferable to those live-fetch tools.

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