agent_send_keys

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

Annotations already declare this is a non-readonly, non-idempotent, non-destructive, closed-world operation, so the safety profile is covered. The description adds the key-encoding model (logical key names in an array, e.g. ['ctrl+c']), but says nothing about whether presses are delivered sequentially, whether the agent must be focused, or whether delivery is acknowledged — notable for a non-idempotent mutation.

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?

One front-loaded sentence with the action first and illustrative values after; every clause earns its place. Slightly dense inline array literals make it marginally harder to scan than plain prose would.

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?

An output schema exists, so return values needn't be explained. But for a non-idempotent UI mutation over two required, undocumented parameters, the description leaves the meaning of 'target' and the focus/ordering behavior unaddressed — an agent could call it wrongly on a valid-looking guess.

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%, so the description carries the full burden. It does a good job on 'keys' via name examples ('esc', 'ctrl+c', 'enter', 'y'), but 'target' — a required parameter — is never explained (agent id? name? UI handle?), leaving half the inputs undocumented in both schema and prose.

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?

Specific verb and resource: 'Send logical key presses to an agent's UI', with concrete key examples that make the action unmistakable. It implies a scope distinction from the sibling pane_send_keys ('agent's UI'), but never names that sibling, so an agent must infer the split itself.

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?

There is no explicit statement of when to use this versus pane_send_keys, agent_prompt, or pane_wait_output. The 'agent's UI' phrasing hints at a boundary, but no condition, exclusion, or prerequisite (agent started/focused) is stated.

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