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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real context beyond them — weekly granularity, whole-week windows ending on the last synced week, default 12 weeks, and the no_data + panel-URL behavior. It stops short of describing pagination or the exact shape of the traffic totals block, keeping it below a 5.

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 the core purpose and view modes, then behavior and use cases; nearly every clause carries information. It is dense but long, and the trailing bilingual Portuguese summary is redundant for an English-reading agent.

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 an 8-parameter read tool with no output schema, the description supplies what is needed: return contents per view, default window, error state, and eligibility check via list_sites. Nothing critical to correct invocation is left implicit.

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 100% so the baseline is 3, but the description adds meaning the schema does not: it explains what each view returns, that the period is in whole weeks ending on the last synced Bing week, and that change is measured against the previous same-length window. This directly clarifies the semantics of view, weeks, and compare.

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 (organic Bing Webmaster performance, weekly) and immediately disambiguates the three modes of the tool (view=traffic vs queries/pages) with what each returns. An agent can distinguish this from the Google-side siblings like get_query_performance or get_timeseries without opening the schema.

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?

Gives concrete use cases ("how do we do on Bing", Bing vs Google query overlap, Copilot-era visibility) and a prerequisite/absent-data path: a property without Bing returns no_data with the connection panel URL, and hasBing in list_sites tells which properties are eligible. That is explicit when-to-use plus how to check eligibility before calling.

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