Drain buffered LCU events

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does an excellent job: it clarifies the cursor semantics, warns about the 'dropped' field indicating data loss from buffer wrap, and explains the 'truncated' field with a concrete remediation path via lol_get. This is strong transparency for a polling tool. It does not, however, state whether polling advances a cursor or clears the buffer (though 'plus the new cursor' implies advancement), and it omits any mention of side effects or read-only guarantees, which keeps it slightly below a perfect score.

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 description is two sentences with zero fluff. It front-loads the primary function (return events since cursor), immediately explains the two special output fields (dropped, truncated) with actionable guidance, and stays tightly focused. Every sentence earns its place without redundancy.

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 polling tool with 3 parameters and no output schema, the description covers the essential elements: the cursor mechanism, the dropped-event warning, and the truncated-data recovery path. It does not specify the full response shape (e.g., whether an empty array is returned when no events exist, or the structure of each event beyond its URI), but given the tool's complexity and the specific edge cases it does address, it is nearly complete for an agent to call correctly.

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 each parameter already has a description in the schema. The description adds value by clarifying that 'since' acts as a cursor from the previous poll, aligning with the tool's sequencing logic. However, it does not add extra meaning for 'limit' or 'filter' beyond what the schema provides. Since the schema carries the heavy lifting, a baseline of 3 is appropriate.

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 states a concrete verb ('Return') and a specific resource ('buffered events') with a precise condition ('seq greater than since') and explicit output elements (new cursor, dropped, truncated). The name 'lol_events_poll' plus the clear behavior distinguishes it from siblings like lol_events_start/stop, and it even references lol_get for re-fetching truncated entries, reinforcing its role.

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 description implies usage: it's a poll operation that drains buffered events, and it gives a concrete instruction to re-fetch truncated entries via lol_get. However, it does not explicitly state when to use this tool versus alternatives (e.g., only after starting event capture with lol_events_start), nor does it mention any prerequisites or exclusion conditions. The usage context is mostly inferable from the name and behavior, not explicitly described.

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