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

The description discloses important behavioral traits beyond annotations: cost ($0.005 per call), datastore life extension (30 days), algorithm (Kahan summation), and value limit (100k). Annotations only indicate openWorldHint=true and non-destructive; description adds critical side-effect and resource consumption details.

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 well-structured sentence that front-loads the core purpose, then lists features, limits, and cost. Every sentence adds value with no redundancy. It is dense yet readable.

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 the tool's complexity (multiple input modes, datastore interaction, paid usage), the description covers all relevant aspects: modes, limits, cost, side effects, and algorithm. An output schema exists, so return values need not be detailed. This is a complete and self-contained description.

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 67% with descriptions for 4 of 6 parameters. The description adds meaning by explaining the three modes (x/y for correlation, rows/field for object arrays, collection for datastore) and clarifying roles. However, 'y' and 'field' parameters lack schema descriptions, relying on the tool description for context.

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 computes exact descriptive statistics (count/sum/mean/median/stddev/percentiles) for various input formats (arrays, paired data, object arrays, datastore collections). It distinguishes itself from siblings by emphasizing exact calculation over LLM's inability to sum, providing a strong purpose.

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 explains when to use the tool (exact stats needed) and provides context like cost, limits, and datastore side effects. However, it does not explicitly state when NOT to use it or compare directly with sibling tools like get_calc (which may offer simpler calculations).

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