Read buffered client console output

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

With no annotations, the description carries the full load and does well: it explains the ts vs pageTs clocks and their difference as a latency signal, discloses that 'reattach' entries bypass every filter because reloads are context, and states that a stopped tailer produces an error rather than an empty result. It stops short of stating read-only/repeat-safety or the cost of large limits.

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 sentences, no filler: purpose first, then the timestamp model, then filter-exemption and failure semantics. The latency-signal framing is dense but front-loaded and each sentence carries information an agent needs.

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 7-parameter, zero-required, annotation-free read tool with no output schema, the description covers timestamp fields, filter-exempt entries, and error behavior, but never describes the shape of a returned entry (message, level, seq) or how cursor and limit interact for pagination. Adequate but with clear gaps.

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 schema already documents all seven parameters and the baseline is 3. The description reinforces cursor semantics and explains that ts bounds (the 'since'/'until' params) are epoch milliseconds on the process's anchored clock, but adds no syntax or format detail the schema lacks.

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?

States a specific verb and resource ('Return buffered console entries') and adds the incremental-read mechanism ('after your cursor'), which inherently separates it from the sibling start/stop console tools. An agent knows this is a cursor-based polling read, not a one-shot dump or a lifecycle control.

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?

The phrase 'after your cursor' implies the intended incremental-polling pattern, and the error behavior hints at a prerequisite (tailer must be running). However, no alternatives are named (e.g. lol_cdp_console_start, lol_events_poll) and there is no explicit when-not guidance, so usage must be inferred.

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