Status, orientation, and next step

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description goes beyond them by disclosing cost ("cheap"), the intended calling cadence, and the shape of the returned state (device, app, budget left, counters, findings, last job, workarounds, readiness) plus nextBestAction with tool/args/why. That is real added value, though it says nothing about failure modes or what happens with an unknown or expired sessionId.

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?

Front-loaded with purpose and cost, then branching cleanly by parameter mode. The parenthetical inventory of state fields is dense but each item is informative; the only mild waste is repetition of the goal-biasing point already implied by the schema.

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?

With no output schema, the description carries the return-value burden and does so compactly: it enumerates the state contents and describes nextBestAction as (tool, args, why), which is exactly what an agent needs to act on the result. For a two-parameter read-only tool this is complete.

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% and the two parameter descriptions already say "omit for orientation" and "bias nextBestAction toward this goal," which the description largely restates. The list of goals (smoke, explore, create_automation_suite, release_gate, test_login, reproduce_bug) and how they actually change the recommendation is left to the enum alone.

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 concrete verb and resource ("session status and the next tool to call") and splits into two clearly named modes: orientation without sessionId, compact state with it. It does not name or distinguish its obvious siblings qa_orientation and qa_job_status, which seem to overlap with those two modes, so an agent still has to infer which to prefer.

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 an explicit usage cadence ("cheap, call between steps") and ties each mode to a situation: omit sessionId for first-call orientation, pass it for a specific session's state. There is no when-not guidance and no direct statement about when to prefer a sibling status/orientation tool instead.

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