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

The annotations include readOnlyHint=false and destructiveHint=false, but the description does not add context about side effects. It mentions specific flags (regenerate=true) and data needs (qid) but does not disclose that many of the listed functions (e.g., insights_share_revoke, insights_theme_frame_delete) are mutating or potentially destructive. Since destructiveHint=false, there is no contradiction, but the description fails to surface the behavioral variance across the enumerated operations.

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 a single long run-on sentence that dumps a massive list of functions with no line breaks or clear structure. It front-loads 'Advanced Insights operations by name' but then becomes a wall of text, making it hard to scan. It could be split into a short overview plus a bulleted list. The density reduces readability without adding proportional value.

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 tool that dispatches over 40 distinct operations, the description is incomplete. It lists function names but does not explain return values, error handling, or how to obtain detailed docs for each function (beyond 'see its docs'). There is no output schema, and the agent is left guessing what each function returns or what side effects to expect. Some functions are mentioned with partial hints, but many are not, leaving significant gaps.

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% (survey_id and fn have descriptions, and params is described as the function's arguments). The description adds extra meaning by giving concrete examples for several functions, such as 'insights_ai_summary with regenerate=true' and 'insights_openend_themes, needs qid'. This goes beyond the schema's generic 'Function name.' and 'Arguments for the function' by linking parameters to real usage scenarios.

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 clearly states the tool's purpose as a dispatcher for advanced Insights operations, enumerating a specific list of function names. It goes beyond a generic 'run function' by naming the exact operations (e.g., insights_ai_summary, insights_pptx) and gives a few usage hints (regenerate=true, needs qid). This distinguishes it from generic tools and aligns with the 'Run an Insights function' title.

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 provide guidance on when to use this tool versus alternatives. It lists many functions but does not mention sibling tools like get_insights_report or get_results, nor does it say 'use this for X, use that for Y'. The only implicit guidance is the list itself, which tells the agent which functions are available here, but it never explains why to choose this over a more specific tool.

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