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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It explains that waiting is not wasted time, that health/mana/soul do not regenerate while HUNGRY or in a protection zone, that food itself heals nothing, that the server rejects more than twenty calls per second, and that the wait returns 'the world after the wait, including everything that happened during it.' This is rich, honest behavioral context that an agent needs to make correct decisions.

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 description is longer than typical, but each sentence earns its place: the use cases, the cooldown rejection context, the two regeneration blockers, and the return value all carry decision-relevant information. It is slightly verbose in the 'twenty per second' server detail, but that specificity is useful for preventing the agent from spamming. Overall it is well-structured with clear emphasis markers.

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 zero-required-parameter waiting tool with no output schema, the description covers everything an agent needs: when to wait, when not to wait, what blocks regeneration, what parameters do, and what the return value contains. The sibling list shows that related actions like eating and moving are handled by other tools, and the description correctly routes the agent to golemreach_use with item 'bread' and to step off the 'P' tile before waiting.

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 100%, so the baseline is 3; the description adds value beyond the schema by explaining that seconds defaults to 3 and maxes at 60, and that untilHealthPercent rests until health and mana reach that percentage or time runs out. The description also frames both parameters in the context of the regeneration rules, helping the agent choose between a fixed wait and a conditional rest.

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 opens with a concrete verb phrase ('Stand still for a while and then report what changed') and lists explicit uses: letting a cooldown lapse, regenerating health and mana between fights, and observing whether a monster approaches. It clearly distinguishes the tool as the intended action for a cooldown rejection, which separates it from siblings like golemreach_attack or golemreach_move.

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 gives unambiguous when-to-use guidance: it is 'the correct response to a cooldown rejection,' explains why retrying immediately is futile, and explicitly warns against rapid repeated calls. It also provides two concrete when-not-to-use conditions with exact remedies: being hungry (eat bread first) and standing on a 'P' protection tile (step outside). This is exemplary usage guidance.

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