list_source_tables

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

With readOnlyHint=true and idempotentHint=true annotations already present, the bar for description-only behavioral disclosure is lower. The description adds the key detail: it returns only source tables not yet in CAS memory and that they are the raw set for promote_table_to_memory. No contradiction with annotations (consistent with read-only, non-destructive). It could optionally mention error behavior for a bad caslib, but the behavioral core is covered.

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?

A tight, two-sentence description with zero wasted words. It front-loads the core purpose in the first line, then immediately connects it to the downstream tool. Fully earns its place.

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 simplicity and the presence of a full output schema plus annotations, the description is complete for the agent to select and invoke it. A minor deduction for not explicitly describing the 'limit' semantics beyond the schema, but overall it's a well-rounded, sufficient 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 description coverage is 100% — all three parameters are well-documented in the schema (e.g., 'Maximum number of tables to return (default 50)'). The description accurately sets up the domain (CAS library, caslib) but adds no new parameter-specific detail beyond the schema. Baseline 3 is correct here.

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?

Purpose is explicitly stated with a specific verb+resource: 'List source tables that are NOT yet loaded into memory in a CAS library.' The critical qualifier 'NOT yet loaded into memory' separates it from sibling tools like list_castables or list_compute_tables. It clearly identifies the exact resource (source tables in a caslib) and the specific state (pre-memory).

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 explicitly declares this is 'the candidates for promote_table_to_memory,' which is the key guidance for a user to know when this is the right tool. It could be a 5 but doesn't explicitly say 'use X for in-memory tables instead' or name an alternative by its full tool name.

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