found_religion

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 well: it specifies the required belief ordering, the conditional pantheon slot ('only if I have no pantheon yet'), the Byzantium bonus-belief exception, and the validity gate. It stops short of describing success/failure outcomes or whether the action is reversible.

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?

Dense but front-loaded, leading with the core verb and target. Multiple nested references (data1, data2, BUTTONPOPUP_..., ENDTURN_BLOCKING_...) make it run-on and hard to scan, but nearly every clause carries operational information rather than 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?

For a mutating game action with no output schema and no annotations, the description covers the precondition, the belief-slot ordering, and the parameter meanings. Missing only downstream effects (what changes once the religion is founded and how failure is surfaced).

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?

At 0% schema coverage the description must compensate, and it largely does: city_x/city_y are tied to the popup's data1/data2, beliefs is explained with its ordering and conditional rules, religion is tied to available_beliefs output, and custom_name's empty-string default is clarified. The mapping for religion is somewhat indirect but all five parameters receive meaning.

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 (found) and resource (religion) plus the activation context (BUTTONPOPUP_FOUND_RELIGION). It is clearly distinguishable from siblings like found_pantheon and enhance_religion. The heavy reliance on raw internal identifiers (data1, data2, blocking_name) slightly muddies the surface but the action is unambiguous.

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?

Provides an explicit gating precondition: 'Only valid when blocking_name is ENDTURN_BLOCKING_FOUND_RELIGION', and routes the agent to available_beliefs(kind="founder").religions for valid inputs. It does not, however, contrast against sibling alternatives such as found_pantheon or enhance_religion.

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