preflight_agent_training_pair

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

With no annotations, the description carries the full burden and does so thoroughly: it reveals the read-only nature despite HTTP POST, enumerates the exact fields sent, disclaims admission/scheduling/launch/persistence side effects, and notes that RBAC is server-derived. The six definitive authority blockers further explain what the response semantics depend on.

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?

The description is around 90 words and front-loads the core purpose in the opening sentence. The second paragraph earns its place by clarifying transport/side-effect expectations, and the blocker list is compact and directly useful for interpreting results. No filler or repetition of schema data.

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?

Despite having no annotations, the description covers purpose, exact inputs, side-effect boundaries, auth context, and the authoritative blocker set. An output schema exists, so return values are documented elsewhere. For a read-only preflight check, this is complete enough for an agent to select and invoke it correctly.

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% and the schema properties only have titles, so the description must compensate. It names all three parameters, marks project_id as optional, and frames revision_id as targeting 'one exact installed action revision.' It could add more detail about installation_id or project_id meaning, but the parameter names plus scope clarification make invocation unambiguous.

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 first sentence states a precise action and scope: 'Read governed-training readiness for one exact installed action revision.' It also explicitly distinguishes itself from mutation siblings by saying it 'cannot admit, schedule, launch, or persist a training pair,' so an agent can tell it apart from tools like request_agent_training_pair_admission or get_agent_training_pair_status.

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?

The description gives strong usage context: it is a read-only preflight and lists six authority blockers that Production treats as definitive, so an agent knows this is the check-before-admission tool. It clearly states what the tool cannot do, but it does not name alternative tools or explicitly say 'use this instead of X,' stopping short of fully explicit routing guidance.

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