flush_observations

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the aggregation method (median per effect), the confidence band written (0.65-0.85, prov="observed"), and the non-destructive rule that higher-confidence dll/static entries are never overwritten, with disagreements stashed in the entry's "obs" field. It still omits whether the accumulated buffer is cleared after flushing and whether repeated calls are idempotent — the main remaining gap for a mutation tool.

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 action and its destination are front-loaded in the first sentence, and each following clause adds non-redundant information about aggregation, provenance, and overwrite behavior. It is dense with domain jargon (prov, dll/static) but no sentence is wasted.

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?

An output schema exists, so return values need not be described, and there are no parameters to document. The description covers the aggregation and persistence semantics thoroughly; the only missing piece is lifecycle detail such as whether flushing drains the observation buffer or requires an active game context.

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 is nothing for the description to disambiguate and no schema gap to compensate for. Baseline 4 for a no-parameter tool.

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 specific verb and target ('Write accumulated card-play observations into card_kb1.json') and explicitly separates this tool from the siblings that generate the data ('play_card / run_turn record before/after state diffs; this tool aggregates them'). An agent can distinguish it from play_card/run_turn without opening any 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?

It establishes clear context: observations are accumulated by play_card/run_turn and this tool persists them, which tells the agent when the tool is relevant. It stops short of an explicit trigger ('call after N turns') or any when-not condition, so it is strong context rather than full routing guidance.

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