set_research

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

With no annotations, the description carries the full burden and does well: it discloses that a free tech is granted outright while current research is left unchanged, and that missing prerequisites cause the game to research the first missing step now and queue the rest. It also names reply fields (`granted`, `goal`, `queue`), which is meaningful behavioral context beyond a bare mutation claim.

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, front-loaded with the primary action, then the free-tech special case, then the prerequisite fallback. Dense with jargon but every sentence adds actionable behavior; only mild readability cost.

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 or annotations exist, and the description compensates by describing the reply fields and the two distinct code paths (normal research vs. free-tech grant vs. queued prerequisites). Complete enough for correct invocation, though it doesn't state valid-value sources or error conditions.

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% and the single `tech` param has no description, so the description must compensate. It does: example values (TECH_POTTERY, TECH_MINING) show expected format, and the special ENDTURN_BLOCKING_FREE_TECH sentinel is explained, including its distinct semantics.

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+resource ('Choose current research') and gives concrete example values, so the agent knows this sets the active research target. It also surfaces a second, non-obvious purpose (claiming a free technology), which is useful disambiguation from siblings like choose_free_great_person or available_research, though it never names an alternative tool explicitly.

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 implies when to use the tool (picking a research target, or passing the ENDTURN_BLOCKING_FREE_TECH blocking name to claim a granted tech), and explains the missing-prerequisite scenario. But it never points to available_research/tech_tree as the source of valid values and gives no when-not guidance, so usage is implied rather than stated.

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