cas_load_info

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

Annotations only declare readOnlyHint=true; the description adds real behavior: no data is loaded, the confirmation gate is driven by SINGLESTORE_MCP_CAS_LOAD_CONFIRM_MB (default 100 MB) and unknown sizes also trigger it, and size comes from table.fileInfo only 'where CAS can tell.' The partial/uncertain size reporting is a useful caveat an agent would not otherwise know.

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 single densely packed sentence, front-loaded with the trigger condition, and every clause carries information (kind, size, confirmation, already-loaded). Nested parentheticals make it slightly hard to parse but nothing is filler.

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 carries the return-value burden and does so by enumerating the four facts returned. For a read-only pre-flight probe the only real gap is the undocumented connection parameter.

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% across three parameters. The description indirectly explains caslib (its kind is inspected) and table (its size is read), but says nothing about the optional 'connection' parameter, nor about expected value formats for caslib/table. Two of three parameters get only indirect treatment and one is entirely unaddressed.

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 enumerates exactly what the tool reports: the caslib's kind (SpeedyStore vs. copied into CAS), the source table's size from table.fileInfo, whether a second confirmation is required, and whether the session already holds the table. The closing 'Nothing is loaded' implicitly separates it from cas_load_table, though the sibling is not named outright.

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 opening 'Before "Load into this session"' gives a clear trigger and positions the tool as a pre-flight check ahead of a load. It does not name the follow-up tool (cas_load_table) or state when to skip the check, so an explicit alternative reference is missing.

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