keyboard

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

With no annotations, the description must fully disclose behavior. It only mentions two actions without explaining side effects, requirements (e.g., keyboard must be visible for dismiss), or return values. Critical transparency is missing.

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?

While extremely concise, the description is under-specified for a tool with 22 parameters and two actions. It prioritizes brevity over clarity and omits necessary context, making it less useful than a slightly longer but complete description.

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?

Given the tool's complexity (many device selectors, action enum) and lack of output schema, the description is insufficient. It doesn't clarify the device context (e.g., mobile keyboard), how action selects behavior, or what the inspect result contains.

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 95%, so baseline begins at 3. The description adds no parameter-level insight; all parameter meaning comes from the schema alone. No improvement over structured data.

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 clearly states the tool manipulates the keyboard with two actions (inspect and dismiss). It is distinct from siblings as no other tool targets keyboard state. However, 'inspect' is vague and doesn't specify what output to expect.

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?

No guidance on when to use this tool versus alternatives. No mention of prerequisites, context, or when not to use it. The action enum provides implicit choices but the description fails to set expectations.

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