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

The description adds crucial behavioral constraints: it explicitly limits the output to 'Metadata/approved fields only' and guarantees 'no secrets, contacts or original files.' This provides significant security and data scope context beyond what the readOnlyHint annotation conveys.

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 definition is concise and professional. It avoids unnecessary jargon and gets straight to the point, efficiently front-loading the core value proposition and scope limitations.

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 that there is no output schema, the description should provide more context on the data structure or the format the query must take. Currently, it only describes the input constraints and output limitations, leaving the agent to infer the structure of the KPIs returned.

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?

Since schema coverage is 0%, the description should explain the semantics of 'limit', 'query', and 'offset.' However, it only presents the available input fields without explaining how they affect the data returned or what kind of data they are designed to query (e.g., date ranges vs. metric types).

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 purpose (reading analytics KPIs) and scope (through the existing application). It differentiates the tool by specifying that it handles 'authorised analytics kpis,' which helps distinguish it from other broader report or dashboard retrieval tools.

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 implies usage for retrieving safe, high-level metrics but provides no explicit guidance on when to use this tool versus a more detailed report (e.g., get_dashboard_analytics) or specific data retrieval.

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