steer

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

No annotations are provided, so the description bears full behavioral burden. It usefully discloses that the operation is non-terminating and mid-run only, but says nothing about what happens if the agent is idle/finished (error? queued?), whether injection is delivered immediately or at the next turn boundary, or whether repeated calls are allowed.

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 tight sentences, action and rationale front-loaded, with zero filler. Every clause carries weight.

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 two-parameter action tool with no output schema, the description covers what it does, when to use it, and why over an alternative. The main remaining gap is failure/edge behavior when the target agent is not running, which is minor at this complexity.

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 100%, with both 'id' (example format ag_7f3k2m) and 'text' documented in the schema itself. The description adds no syntax, format, or constraint detail beyond what the schema already carries, so the baseline 3 applies.

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?

Names a precise verb+resource: inject a message into a running agent's turn. It immediately distinguishes itself from the stop sibling by stating it works 'without killing its work', so an agent can tell it apart without opening the 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?

Explicitly says to 'use this to correct course mid-run' and names an alternative (stopping and re-prompting) with a claim of superiority. It does not draw the boundary against the sibling 'follow_up' (presumably for after a run ends), so the exclusions are incomplete.

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