agent_send_keys

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

No annotations are provided, so the description carries the full burden. It discloses the authorization model (orchestrator pre-approval, runtime does not grant approval or decide escalation) and constrains the key set to bounded control/navigation keys. It does not state rate limits, whether keys can be lost, or what is returned, but the policy context is unusually rich.

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?

Three sentences, all carrying load: the action and its authorization precondition first, then the runtime's non-decision, then the redirect to the sibling. No filler, though the middle sentence is dense enough to read as policy boilerplate.

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 2-parameter mutation tool with no annotations and no output schema, the description supplies the missing safety and routing context. It omits any statement about effects on the terminal or return behavior, but the authorization framing covers the highest-risk unknowns.

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 50%: agentId is documented in-schema as the ID returned by agent_start, while keys has no schema description. The description compensates by describing the keys parameter as bounded control/navigation keys, which explains the enum's intent. It adds meaning beyond the raw enum list without repeating 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 (send), specific resource (bounded control/navigation keys) and the target (an MCP-managed agent terminal). It explicitly distinguishes itself from the sibling agent_prompt by routing arbitrary text there. An agent can tell the two apart without opening a schema.

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?

Gives explicit preconditions: only after the orchestrator has inspected the current interaction and determined the action is authorized. Names the alternative for the excluded case (arbitrary text must use agent_prompt). Both the when and the when-not are stated.

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