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

Annotations already declare destructiveHint=true and idempotentHint=true, so the destructive profile is covered structurally. The description adds real value beyond them by specifying what must be carried over (unchanged blocks, IDs, audience, browserContinuation.fromBlockId) and by clarifying scope with 'No launch.' It doesn't address auth or whether the definition can be recovered.

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, front-loaded fragments with no filler; the replacement scope and preservation rule come first. The telegraphic fragments ('No launch.') are dense but slightly cryptic, which keeps it just below a 5.

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 highly nested mutation tool with an output schema and rich annotations, the description covers the essentials: it is a full replace, it is advanced/prefer smaller edits, it does not launch, and it lists what must be preserved. The main omission is that it never flags the optional construction decision-tracking parameter.

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 roughly 50%, and the description touches the definition payload only indirectly, via 'audience' and 'browserContinuation.fromBlockId'. It says nothing about testId format, the optional construction array, or that expectedRevision is ignored, so it adds modest value over the schema rather than compensating for the coverage gap.

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+resource ('replace the COMPLETE definition') and flags its advanced, whole-object nature, which distinguishes it from granular siblings like update_test_block or update_task. It does not, however, name those siblings, so an agent must infer the boundary from the phrase 'Prefer targeted edits.'

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?

'Advanced' plus 'Prefer targeted edits' gives a clear when-to-use/when-not signal: reach for this only when a wholesale replacement is needed. It stops short of the 5-level bar because the targeted-edit alternatives (update_task, update_test_block, set_test_audience, set_test_construction) are never named.

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