Report your activity to the mascot

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

The description discloses that repeating the same state does not re-announce it, which complements the idempotentHint annotation. It also clarifies that 'succeeded'/'failed' are terminal and clear themselves, and 'idle' removes the display—behavioral details beyond what annotations state. This is consistent with the annotations and adds useful context.

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 three sentences, starts with the core purpose, and immediately offers practical usage patterns. It front-loads the most important information (what it does and when to call it) and avoids unnecessary detail, earning its place.

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 tool with an output schema (not shown but indicated) and 5 well-described parameters, the description covers the essential usage scenarios, state lifecycle, and safety of repeated calls. Nothing critical is missing for an agent to invoke it correctly.

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 100%, so every parameter is documented. The description adds a small extra by mentioning 'optionally with a short label' and grouping states into ongoing vs terminal, which enhances understanding. However, it largely repeats the schema's state descriptions, so it does not dramatically exceed the baseline for high coverage.

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 states a specific verb (report) and resource (AI Coach mascot activity) and explains exactly what happens: the mascot shows your current doing via animation and speech bubble. It distinguishes itself from siblings by focusing on activity reporting rather than notes, dashboard, or care operations.

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?

It gives explicit guidance on when to use each state: 'thinking'/'working' when starting a task, 'waiting' when needing the user, 'succeeded'/'failed' when finishing. It also notes that repeating the same state is harmless, so it can be called on every step, which prevents unnecessary calls and clarifies the intended frequency.

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