search_across_instances

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral grounding with 'fanned out... merged and attributed', which explains the cross-instance orchestration and result attribution. It does not go into detail about attribution semantics or edge cases, but it complements the annotations well.

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?

This is a single, well-structured sentence that front-loads the key idea ('Read-only') and packs in scope and behavior without waste. It is concise while still being information-dense.

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?

Within its parent object schema and annotations, this description is reasonably effective, and an output schema covers return value semantics. However, main gaps are the lack of parameter semantics and no explicit guidance around when to select this instead of related search_records or aggregate_across_instances. It is minimally complete but not richly enough for a complex fan-out tool.

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 0%, and the description provides essentially no parameter guidance. Parameter names like model, domain, instances, and limit_per_instance are somewhat self-explanatory, but the semantics of null defaults, the format of domain/instances, and how limit is applied are left unexplained.

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 ('search'), names the resource (Odoo instances), and conveys a precise scope ('fan out across configured instances', 'merged and attributed'). It clearly distinguishes this from single-instance search_records and aggregate_across_instances.

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 phrase 'fanned out across configured Odoo instances' clearly indicates the main use case is multi-instance search. It does not explicitly name alternatives or list when not to use it, but the context is clear enough for an agent to choose it over search_records or aggregate_across_instances.

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