topic_cluster_performance

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

With no annotations provided, the description carries the full burden. It explicitly discloses important behaviors: base analysis only on returned data, report exact numbers, do not speculate, say when information is insufficient, and always present results as interactive visualizations with specific design elements. This goes beyond simple API behavior to govern how the agent should interpret and present results.

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 structured with a main purpose statement followed by IMPORTANT and PRESENTATION sections. While this adds structure, the PRESENTATION section is lengthy and prescriptive, containing detailed visual design instructions that could be more concise. It is not tightly packed but still has a clear hierarchy.

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?

The description explains what metrics are aggregated and mentions top pages and queries, but it lacks details on how path_pattern matching works (exact match, prefix, regex), data format, or pagination. Since there is no output schema, the description should compensate for these gaps, but it only partially does so. The analysis guidelines are valuable, but the return structure is under-specified.

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 100%, with both 'days' and 'path_pattern' documented in the schema. The description adds no new parameter semantics; it only mentions 'URL path pattern' which mirrors the schema. Thus the baseline 3 applies.

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 ('Aggregates') and clearly states the resource ('all pages matching a URL path pattern') and the output (clicks, impressions, CTR, position, top 5 pages and queries). It distinguishes itself from sibling tools by focusing on group performance rather than individual URLs or specific opportunity types.

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 does not state when to use this tool vs alternatives. It gives no context for choosing it over sibling tools like 'site_snapshot' or 'advanced_search_analytics', and no mention of exclusions or prerequisites. The only guidance is about data handling, not tool selection.

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