agent_prompt

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

Annotations only declare it as a non-readonly, non-idempotent mutation; the description adds the substantive behavior the annotations can't express: blocking semantics, the default settle states, the override via 'until', and a named error condition (agent_blocked). It omits what happens when the block exceeds the timeout, which is the main remaining behavioral unknown.

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 sentences, no filler. The core action comes first, then the blocking/error semantics; every clause carries information an agent needs.

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 5-parameter blocking mutation, the absence of any timeout_ms guidance or timeout behavior leaves a gap in an otherwise tight definition.

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 description coverage is 0%, so the description must carry all parameter meaning. It explains wait, until (matching the enum values idle/done/blocked), and implies target/text, but timeout_ms (default 120000) is never mentioned — a critical omission for a call that blocks by default.

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 — 'Submit a prompt to an agent' — which is distinct from sibling tools like agent_send_keys (keystrokes) and agent_wait (passive waiting). It never names a sibling explicitly, so the differentiation is inferred rather than stated.

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?

'With wait=true, block until the agent settles' tells the agent when to choose blocking behavior and how 'until' overrides the default settle set (idle, done, blocked). The rejection case 'agent_blocked if the agent is already waiting at a dialog' is a real precondition that steers the caller away from an invalid call, though it never points to an alternative tool for that situation.

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