aggregate

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

With no annotations, the description carries the full disclosure burden. It adds meaningful traits — server-side execution, grouped output capability, and a performance/precision claim — but leaves key behaviors undisclosed: no explicit statement that it's a read-only operation, no mention of result limits (e.g., max groups returned), and no indication of the return shape despite there being no output schema.

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?

Two dense sentences with zero waste: the core function is front-loaded in sentence one, examples follow, and the rationale closes in sentence two. Each clause earns its place, and nothing is repeated from the schema.

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 with 8 params, no annotations, and no output schema, the description covers the aggregation semantics well but leaves gaps: how to address the data source (layer_id/layer_key/service_path is undocumented in both schema and description), what the response looks like (single record vs. grouped rows), and the where/order_by behavior. An agent could still invoke it correctly on the required params, but the peripheral params remain a mystery.

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 only 25%, but the description richly illustrates the interaction of the two required params (stat_type, field) plus group_by via examples ('count parcels per district' implies stat_type=count, field=parcels, group_by=district). It does not compensate for the six undocumented params — where, order_by, layer_id, layer_key, service_path — which are essential for actually targeting the data source.

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 (aggregate) on a specific resource (server-side data) with the full operation set enumerated (count/min/max/avg/sum). Concrete examples — 'count parcels per district, average sensor AQI, max reading date' — make the semantics immediately graspable and distinguish it from siblings like query_layer (raw rows) and count_features (count only).

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?

Provides clear context for when to use it: 'Cheaper and more precise than pulling rows and summing client-side' implicitly positions it against row-returning alternatives. However, it never names specific sibling tools, doesn't state when NOT to use it (e.g., simple counts could use count_features), and doesn't mention prerequisites like layer identification.

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