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

Annotations already declare idempotentHint, destructiveHint, readOnlyHint and openWorldHint, so the description's repetition of idempotency adds nothing. Its one genuinely new behavioral fact is the once-per-local-day rate limit, which is real context beyond the annotations; failure modes, permission requirements and side effects remain undisclosed.

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 front-loaded sentences with no filler; the daily cadence constraint leads. It is efficient, though the extreme terseness borders on under-specification rather than optimal concision.

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?

A mutation tool (readOnlyHint=false) with no output schema and zero parameter documentation needs the description to carry return value, effect and permission context, and it does not. An agent learns the cadence and parameter exclusivity but not what a successful light produces or what happens on failure.

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 schema has no oneOf/anyOf, so the description is the only place stating that 'auto' is mutually exclusive with an 'owned' wishId/shrineId target — that is meaningful added semantics. However, it does not explain what wishId vs shrineId refer to, why the schema pins auto to const true, or what counts as 'owned'.

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 verb+resource ('Light incense') largely restates the tool name, and the description never says what lighting actually accomplishes in the game/domain or what it grants the agent. It adds the once-per-local-day cadence, which is informative, but an agent cannot distinguish this from make_wish or draw_oracle on stated effect alone.

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?

The description constrains parameter choice ('Use auto or one owned target') but gives no guidance on when to call light_incense versus its siblings (make_wish, find_shrine, draw_oracle). There is no when-to-use, no prerequisites, and no exclusions.

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