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

Annotations already declare a non-readonly, open-world, non-idempotent operation. The description adds meaningful behavior beyond that: the complete set of permitted emote strings and the fact that walking terminates the current emote. It still omits duration, persistence, and prerequisite state such as being inside the oasis.

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?

Two short sentences, front-loaded with the valid values and followed by the key termination rule. Every phrase carries usable information.

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 small emote tool with annotations covering mutability and safety, the description supplies the essential input domain and one important behavioral rule. It could be more complete by stating that the agent must already be in the oasis and by clarifying what a successful call returns.

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 only 50%, and the 'emote' parameter is a bare string with no enum in the schema. The description compensates substantially by enumerating all valid values, including variants like dance:1 through dance:3. The token parameter is already explained in the 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 and resource: perform an emote with a closed list of supported values. It is distinguishable from oasis_say and oasis_move by being body-expression rather than speech or movement, though it never explicitly contrasts with those siblings.

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 enumerated values implicitly guide valid usage, and 'Walking ends an emote' gives one context rule. However, there is no explicit when-to-use guidance or alternative routing versus oasis_say, oasis_move, or idle behavior.

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