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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description adds valuable behavioral context: pages of 50, default sort by opportunity, position sorted best-first with unranked last, null positions when Google Search Console is not connected, and the fact that keyword_id is reused by other tools. This is exactly the kind of context that goes beyond structured 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?

The description is dense but every sentence carries operational value: returned fields, pagination, sorting, filtering, null behavior, downstream ID usage, and multi-website prerequisite. It is front-loaded with the core purpose and does not waste words on tautology or 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?

Given an output schema already exists and there are 5 optional parameters, the description covers all call-time decisions: pagination size, sort options and default, filtering approach, website_id prerequisite, null positions edge case, and the tool's role in the broader keyword toolset. No essential information for invoking the tool correctly is missing.

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 80%, so the baseline is 3andar; the description earns above baseline by adding semantics not present in the schema: page size of 50, sort order details ('position (best first, unranked last)'), default sort by opportunity, and the account-specific reasoning for website_id. Some overlap exists for search and favorites_only, but the added context is meaningful.

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 uses a specific verb and resource, 'Lists the website's tracked keywords', and enumerates the exact fields returned, which leaves no ambiguity about what the tool does. It further differentiates the tool from siblings by stating that it returns keyword_id values used by every other keyword tool, establishing it as the canonical listing endpoint.

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 description gives clear operational context: pagination, supported sort orders, filtering options, and when to pass website_id ('when the account has several websites'). It doesn't explicitly name alternatives or state when-not to use it, but the role as the source of keyword_id values strongly implies when it is needed.

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