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

With annotations already declaring destructiveHint=true and idempotentHint=false, the description adds real behavioral context: automatic dedup, a 1-200 batch bound, mixed-list tolerance, and that adding does not trigger the paid rank check while intent/funnel_stage are persisted. It does not explain whether existing tracked keywords are overwritten, but the added operational detail goes meaningfully beyond the 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?

Front-loaded with the core purpose, then format, examples, and follow-up tools in a logical order. The two worked examples earn their space, though the run-on parentheticals make it denser than strictly necessary.

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 two-parameter mutation tool with no output schema but full annotation coverage, the description supplies enough to call it correctly: accepted formats, field enums, limits, and follow-up tools. Only the effect on pre-existing tracked keywords is left unaddressed.

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% (baseline 3), yet the description still adds substantial meaning the schema omits: it enumerates allowed intent values (informational/commercial/transactional/navigational), funnel_stage values (tofu/mofu/bofu), the extra optional fields (cluster_name, notes, source), the accepted string-vs-object formats, and the 1-200 count limit.

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 ('Save target keywords to a brand's account') and immediately clarifies the scope as the keywords the user decided to track. It names sibling tools (list_tracked_keywords, get_keyword_funnel) so an agent can distinguish saving from recalling and reviewing.

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 clear context for use ('the keywords you and the user decided to track and build for') and routes follow-up work to list_tracked_keywords and get_keyword_funnel. It stops short of naming true alternatives like remove_tracked_keywords, promote_research_keywords, or seed_keywords_from_gsc, so it is strong but not complete on when-not/alternatives.

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