post_upgrade_verify

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

No annotations are provided, so the description carries the full burden. It describes the output (surfacing failures, recovered, unchanged) and outcomes, but does not disclose if the tool modifies state (e.g., creates a snapshot) or if there are side effects. The phrasing 'Take a fresh post-upgrade snapshot' suggests a possible mutation, but it is ambiguous.

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?

Three sentences: first states the action, second lists what is surfaced, third defines outcomes. No redundant information, and each sentence earns its place.

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?

The description covers the key outputs and outcomes, and with only one well-documented parameter, it is fairly complete. However, it does not explain the format of the returned data or explicitly state the prerequisite of having a pre-upgrade snapshot, though this is implied.

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?

The only parameter (pre_snapshot_id) has 100% schema coverage, but the description adds value by specifying it is 'the snapshot_id returned by pre_upgrade_snapshot', which clarifies its origin beyond the schema description.

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 clearly states what the tool does: takes a fresh post-upgrade snapshot and diffs against a pre-upgrade snapshot, surfacing new failures, recovered checks, and unchanged failures. It also defines the outcome categories (success/degraded/regressed). This distinguishes it from siblings like pre_upgrade_snapshot.

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 implies usage is after an upgrade and after a pre_upgrade_snapshot has been taken. It is clear about the context but does not explicitly state when not to use it or mention alternatives like regression_catalog.

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