set_faith_purchase

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

No annotations are provided, so the description carries the full burden. It does disclose an important failure mode (the call is refused for unlisted options) and enumerates accepted values, which is more than nothing. But it says nothing about permissions, side effects on existing settings, or what happens to the current selection, leaving meaningful gaps 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?

Three short sentences, front-loaded with the tool's identity and immediately followed by the enum values and index source. No filler, and the guard clause closes it out. The dense backtick notation is slightly cryptic but efficient.

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 low-complexity two-parameter mutation tool with no output schema and no annotations, the description covers purpose, allowable values, value source, and the refusal condition. It omits return/effect confirmation, which is a minor gap given there is no output schema to lean on.

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 description coverage is 0% with no enums in the schema, so the description must compensate, and it largely does: it lists the valid `kind` values (nothing, save_prophet, unit, building) and explains `index` as the unit/building id drawn from religion_overview().auto_purchase.options. It does not clarify when `index` is meaningful or what the default 0 implies, but this is strong compensation over the bare schema.

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+resource: it sets the Religion Overview's automatic faith purchase pull-down. The valid `kind` values are enumerated, so an agent can tell this configures an auto-purchase setting rather than performing a purchase or choosing a great person. It does not explicitly contrast with nearby siblings like choose_faith_great_person or religion_overview, but the resource 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?

Usage is implied by pointing to religion_overview().auto_purchase.options as the source of valid index values, and the final sentence gives a real constraint: 'Refused for anything the pull-down does not currently list.' However, it never explicitly frames when to reach for this tool versus the sibling selection tools. Guidance is present but partial.

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