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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds meaningful behavior beyond that: it describes the fallback path when relocating code fails ('how much markup to cut or text to add') and the detector's stop condition, which helps the agent anticipate output shape.

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?

It is a single dense sentence, front-loaded with the tool's purpose before enumerating contents, and the parameter instruction is placed last. Every clause carries information, though the run-on structure makes it harder to scan than it could be.

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 and zero required parameters, the description takes on the job of describing return values and does so thoroughly, including the fallback branch. Nothing critical is missing, though alternatives for adjacent tasks are not addressed.

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 only 50% (domain has no schema description), but the description compensates by stating that domain is fetched now while id replays a stored scan, giving semantic meaning to both parameters. This is exactly the context the schema omits, so it rises above the baseline.

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 pins down a specific resource: a fix plan for the PAGE_IS_MOSTLY_CODE finding, with breakdowns of bytes by category, largest blocks, and ordered steps. This clearly separates it from sibling fix_* tools that target other findings (fix_robots, fix_entitymap, fix_machine_chain). It never states a verb like 'generate' or 'compute', but the purpose is discernible.

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 closing sentence 'Give domain (fetched now) or id (a stored scan)' does explain the two input modes and their effect, which is useful. However, it gives no explicit when-to-use vs. when-not guidance relative to siblings like explain_finding or scan_domain, so the selection context is only implied.

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