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

Annotations already cover readOnly/idempotent/non-destructive, and the description goes well beyond them: it explains that a referral bonus is independent of share limits but shares active-campaign capacity, enumerates verdict.reason states with remediation (publish first, upload covers, ask again shortly), and describes the PENDING→RUNNING polling lifecycle. This is substantive behavioral context an agent cannot get from structured fields.

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 the key non-mutation boundary before the dense field/enum detail. The middle is a long run-on covering many fields, but given there is no output schema each clause carries information, so it is verbose without being wasteful.

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 full burden of explaining return values, and it does: verdict/offer/referralOffer semantics, remainingFreeRuns, durationDays, budgetUsd accounting caution, and current/runs shapes with status and failureReason. Nothing essential for correct interpretation is missing.

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?

Single applicationId parameter with 100% schema description coverage ('as returned by list_applications'), so the schema carries the semantics. The description adds nothing about the parameter itself, making the baseline 3 appropriate.

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 (Read) and resource (campaign eligibility, bonus offers, existing traffic runs for this game), and explicitly bounds scope with 'This read does not launch a campaign or spend a traffic bonus,' cleanly separating it from start_sandbox_traffic. An agent can distinguish it from get_sandbox_share and get_sandbox_state from the text alone.

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?

Clear context for the read and routes the agent to get_bridge_sdk_docs when NO_BRIDGE is returned, and tells the agent to poll runs after a start. It does not explicitly name when to prefer get_sandbox_share or get_sandbox_state over this tool, so the sibling boundary is implied rather than stated.

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