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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: gsc returns empty when Search Console is not connected, dfs is cached 7 days per site and spends money on a cold cache, auto falls back automatically, and the tool is available on any plan. Those are the operational traits an agent needs before spending credits.

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?

The key fact (what is ranked, with movement) is front-loaded, and the per-source semantics follow in a tight sequence. It is dense but every clause adds decision-relevant information; only the parenthetical nesting of source details makes it slightly harder to scan.

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 read tool with no output schema, the description covers sourcing, cost, availability, and filtering thoroughly enough to call it correctly. It only lightly characterizes the return shape ('position and movement') and never mentions paging behavior, which would be the remaining gap.

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 behavioral meaning the schema lacks: the enum values' cost and freshness semantics, the fallback behavior of auto, and the branded=false filtering shortcut. It does not explain the limit/offset paging interaction, which the schema already covers.

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 (what the site currently ranks for) and immediately scopes it with the returned fields (position and movement). It also names the sibling run_rank_scan as the different, heavier operation, so an agent can separate the two without reading either 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?

Explicitly describes when each source mode applies (gsc = free/exact, dfs = paid/cached estimate, auto = prefer GSC with fallback) and gives a concrete filtering rule (branded=false for non-branded only). It also routes the agent away when a full scan with difficulty scores and Lighthouse is wanted, naming run_rank_scan.

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