copilot_steer

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

With no annotations, the description carries the full burden and does it well: best-effort delivery, possible additional allowance consumption, no rollback of prior work, non-idempotent, and scope bound by the job's original sharing attestation. These are exactly the mutation risks an agent needs before calling.

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?

Four short sentences, zero filler, with the core action leading and the risk disclosures following in descending order of importance. Each sentence adds distinct operational information.

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 mutation tool with no annotations, no output schema, and 0% schema description coverage, the description covers the critical behavioral risks. It is thin only on parameter constraints (UUID format, prompt length) and on what a successful call returns or how to confirm the correction took effect.

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% across two parameters, so the description must compensate; it only partially does. It implies jobId identifies the target running job and prompt is the correction text, but says nothing about the UUID format or the 20,000-character prompt limit.

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 names a specific verb and resource ('send a best-effort correction to a running job') plus a timing boundary ('before its next model request'), which separates it from start/apply/cancel style siblings. It stops short of naming an explicit alternative, so the differentiation is implied by scope 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?

It gives usable context: use while a job is running, restrict corrections to the original authorized scope, and inspect events before retrying. That last clause effectively routes the agent to the events tool, though no sibling is named outright and no explicit 'do not use for X' exclusion is present.

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