cas_load_table

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds real behavioral context beyond them — the write is session-scoped and never promoted, the caslib itself is untouched, and large copies are gated behind a ``needs_confirmation`` response. It does not say what happens to a pre-existing session table with the same name on a repeat load, which is the remaining meaningful gap.

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?

Front-loaded with the act and its scope, then parameters, then the confirmation rule, then the return shape — a sensible decision order for a caller. The telegraphic compression (backticked keys, 'SpeedyStore caslibs ignore ``where``') is dense but every clause conveys information.

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?

With no output schema, the description helpfully explains what comes back — ``live`` (queries run in SingleStore) or copied into CAS memory with byte counts — and warns of the ``needs_confirmation`` branch. For a 6-parameter mutation tool the only real omission is the untouched ``connection`` parameter and repeat-load semantics.

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 0%, so the description must carry parameter meaning, and it does for the important ones: ``where`` and ``columns`` narrow a copy (with SpeedyStore ignoring ``where``), and ``confirmed`` is the explicit unblock for the confirmation prompt. ``connection`` is only obliquely implied by 'the SAS Viya connection' and gets no dedicated semantics.

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 operation (loadTable of a caslib's source table into the Workspace CAS session) and names the exact scope (session only, never promoted, caslib unchanged). It is clearly distinguishable from cas_unload_table, cas_reload_tables, and cas_tables, and even names the downstream reason (FedSQL in CAS can query it).

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 makes the conditions concrete: use it when you need the table queryable by FedSQL in CAS, use ``confirmed`` when a copy is big or unknown-size, and note that ``where`` is a no-op on SpeedyStore caslibs. It stops short of explicitly contrasting with sibling tools such as cas_reload_tables or load_file_start, so there is no stated when-not-to-use.

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