traffic_drop

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

With no annotations, the description carries the full burden, and it does disclose one important trait: the return value is a set of instructions to execute verbatim rather than a summary. That is genuinely useful and non-obvious. It still says nothing about whether the call mutates anything, permissions, scope of the diagnosis, or cost/latency despite the 'in cost order' phrasing.

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?

Two tightly written sentences with the diagnosis and its ordering front-loaded, followed by the output-handling instruction. Every clause earns its place, though the second sentence's phrasing is slightly awkward ('carry them out rather than summarising them').

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 tool with no annotations, no output schema and four optional parameters, the description is adequate: it establishes the diagnostic entry point and tells the agent what to do with the result. It leaves gaps on how this relates to the sibling audit/refresh tools and on the shape of the returned instructions, so it is minimum viable rather than 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 all five parameters carry their own descriptions with examples, so the baseline is 3. The description adds no additional semantics such as how 'shape' values map to diagnosis paths or how 'region'/'tongue' affect the returned instructions, so nothing lifts it above 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?

States a specific verb and resource ('Diagnose lost rankings or traffic') and adds the diagnostic order it enforces (rendering, indexing, crawl before algorithm update). It is clearly distinguishable in domain from siblings like gsc_audit or content_refresh, but it never names or contrasts an alternative, so it stops short of a 5.

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 trigger condition (rankings or traffic have dropped) is implied by the opening phrase, and the description usefully cautions against jumping to an algorithm-update conclusion. However, it gives no explicit when-not guidance and does not route the agent to or away from any sibling tool, which is the main thing an agent needs at selection time.

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