describe_sap_table

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

With no annotations supplied, the description does carry the load and it discloses one important trait: results are cached for 7 days and refresh re-reads from SAP. That is genuinely useful. It does not state the operation is read-only, whether the refresh invalidates the cache for all callers, or what happens when the table does not exist.

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?

Two dense sentences with no filler, and the returned-field list is front-loaded before the parameter notes. The telegraphic, semicolon-heavy style is slightly harder to parse than plain prose, which keeps it off a 5.

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 simple 3-parameter lookup tool with an output schema that already documents the return shape, this covers the essentials: what comes back, cache behavior, and both optional switches. Only the missing read-only/nonexistent-table behavior and sibling routing leave a gap.

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 compensate and it largely does: 'search filters by name or description' clarifies the matching semantics that the bare string type does not, and 'refresh re-reads from SAP' explains the boolean's effect. The required 'table' parameter is left implicit but is self-evident from the tool name and first clause.

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?

Names the resource precisely and enumerates what comes back for each field (name, type, length, key, description), which makes it distinguishable from data-returning siblings like read_sap_table and aggregate_sap_table. The verb is only implied by the tool name, but the payload description removes any real ambiguity.

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?

Explains what the search and refresh switches do, which implies the two usage modes (look up a subset by name/description, or force a re-read), but it never states when to prefer this over read_sap_table or get_service_metadata. No exclusions or prerequisites are given.

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