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

Annotations already flag destructiveHint, but the description adds crucial behavioral context: deletion is irreversible, a broad WHERE clause deletes all matching records, single-record deletion requires a unique field filter, and the call returns the deleted count. These go well beyond the structured annotations.

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 multi-sentence but every sentence contributes essential guidance: purpose, irreversibility, WHERE semantics, single-record strategy, return count, and field-name sourcing. It is front-loaded with the core action and remains tightly organized without redundancy.

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 destructive tool with no output schema, the description fully covers what an agent needs: required WHERE clause, broad-delete danger, irreversible nature, return value, prerequisite discover_tables call, and field-name validation. Nothing critical is left to inference.

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 100%, so the baseline is 3. The description adds extra meaning for the 'where' parameter: Microsoft SQL Server syntax support, case-insensitive field names, and a warning that field names must come from discover_tables. It also reinforces that tableId must be the discovered ID, not a name.

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 states a specific action ('Deletes one or more records'), a specific resource ('a Caspio table'), and a precise selection criterion ('match the WHERE clause'). It clearly differentiates from view-related siblings by scoping to tables and mentioning tableId from discover_tables.

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 gives clear context: use this tool to delete table records matching a WHERE clause, call discover_tables first, and avoid guessing field names. It does not explicitly name delete_view_records as an alternative, but the table-vs-view distinction is clear enough from context.

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