get_events

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

No annotations are provided, so the description carries the full burden and does well: it discloses the return envelope ({events, last_seq}), the cursor-based incremental retrieval pattern, and the retention limitation that state does not survive server restarts. It stops short of describing event `kind` values or ordering guarantees.

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?

Four tight sentences, front-loaded with what the tool returns, then the cursor mechanism, then the retention caveat. No filler, no restatement of the tool 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 supplies the response shape and cursor semantics, plus the lifecycle limitation — everything needed to invoke and iterate correctly. Minor gap: the set of possible `kind` values is elided as "...", which could matter for client-side filtering.

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%, so the description must compensate, and it does: `since` is defined as a sequence number, and the round-trip use of `last_seq` gives a concrete value to pass. Only the default-0 baseline behavior (fetch everything retained) is left implicit.

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: retrieves self-initiated messages TTSim emitted (print output, Lua errors, game loaded/saved, object creation). This clearly separates it from siblings like get_scripts (script inventory) and run_lua (execution), which do not describe an event stream.

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?

Explains the polling pattern explicitly: pass the returned `last_seq` as `since` next time to get only new events. It also states the key exclusion — only events received while the server runs are available — so the agent knows not to rely on history. It doesn't contrast with sibling tools, but the usage context is clear.

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