turn_digest

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

With no annotations, the description carries the full burden and does meaningful work: it explains that unit_destroyed on a trade-route turn is normal (route becomes a unit), that unit_graphics_reset only means a model was rebuilt, and that unit_captured is a civilian taken rather than killed, including the payload fields that row carries. It does not cover authentication, rate limits, or the temporal window beyond "since my last call."

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?

Front-loaded with the one-line purpose, followed by edge-case notes that each earn their place by disambiguating confusing event types an agent would otherwise misread. Slightly dense and run-on toward the end, but nothing is redundant filler.

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?

No output schema exists, so the description must characterize the return, and it largely does — it names the event categories delivered and gives payload detail for at least one event (unit_captured). Gaps remain on overall structure and how far back the digest reaches, but for a zero-param digest tool this is close to complete.

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?

The tool takes zero parameters, so there are no semantics to explain; the baseline for a no-parameter tool is 4. The description correctly implies no input is required by framing it as an automatic since-last-call digest.

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-like function and scope ("Everything recorded since my last call") and enumerates the content categories (combats, cities, wars, chat, notifications, alerts). It distinguishes itself by naming related siblings (negotiate_deal/propose_deal) in the exclusion note, though it never contrasts itself with nearby tools like notification_log, briefing, or turn_status.

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?

Usage is implied — call it to catch up on events since the previous call — but there is no explicit when-to-use/when-not, nor a pointer to turn_status or notification_log as alternatives for overlapping needs. One partial boundary rule is given (self-provoked leader lines from negotiate_deal/propose_deal are excluded), which helps but doesn't constitute full guidance.

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