bw_read_metadata_tables

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

With no annotations, the description handles the behavioral disclosure: it states it read-only, requires ADT authorization, is backed by the ADT DataPreview service, and describes a subtle ordering trait for RSPC (parallel branches have no fixed order, so the agent must read an "After" line to get the actual dependency). It doesn't describe the entire return shape, but the per-type notes already hint at the returned content quite clearly.

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 long but every sentence carries load: fallback role, system-profile check, supported types, an important delimiter for RSPC, an official auth requirement, and the preferred alternative. It introduces the core read-only behavior first and then builds from that description without repetition.

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 2-param, no-output-schema tool, the description is almost complete: it covers target object types, when to use, the correct alternative, how to discover it, auth, and even an unusual ordering caveat for process chains. A small gap, it could explicitly comment on the raw format or content returned, but the object-type notes already imply at least the high-level response shape.

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?

The input schema already has 100% description coverage for both parameters, so the baseline is 3. The description adds meaningful extra context by clarifying the object_name format (UUID-like for TRFN) and giving semantic details about each object_type, especially RSPC ordering and TRFN routine source quoting.

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?

It has a specific verb and resource — “Read a BW object definition directly from its metadata tables (via AD object definition directly from its metadata tables (via ADT DataPreview service)” — and lists every supported object type. It also distinguishes itself from sibling REST-based readers by calling out “Read-only fallback for object types the connected system does not publish as a REST resource.”

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?

It explicitly tells the agent when to prefer an alternative (“Prefer bw_get_transformation where the REST endpoint exists”), when the tool is meant to be used (fallback when no REST resource is published), and how to verify that (“Use bw_system_profile to see which endpoints a system publishes”). This covers both the when and the when-not condition.

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