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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds real behavioral context: the early/middle/late binning and the fact that engines lacking raw_answer (Bing, Brave) return 'unknown'. It stops short of describing the output shape or edge cases like multiple matches, but adds meaningful value beyond annotations.

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 tight sentences, front-loaded with the core purpose and followed by mechanism, value framing, and the key limitation. Every sentence earns its place with no filler.

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?

An output schema exists so return values need no explanation, and the description covers purpose, mechanism, and the engine limitation thoroughly. Slightly short on routing guidance versus sibling citation tools, but otherwise 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 coverage is 100%, so the baseline is 3, but the description adds engine-specific semantics ('engines without raw_answer... return position unknown') that reinforce the engine param's enum behavior in a way the schema only partially conveys.

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 ('Locate where each cited URL appears in the AI's raw answer text') and describes the mechanism (bins char position into early/middle/late thirds). It is clearly distinguishable from siblings like citations_check and signals_ai_overview.

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?

Provides implied context (measuring citation position) and notes which engines yield 'unknown', but never states when to choose this over citations_check or signals_ai_overview, nor any exclusions beyond the engine caveat.

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