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

Annotations already declare destructiveHint=true, but the description adds significant context: deletion is 'Permanent,' the where clause must be non-empty, exact matches, and the call 'Returns how many were deleted.' These details go beyond the annotation and materially shape an agent's expectations.

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 compact sentences with zero filler. The core operation and the critical constraint are front-loaded, followed by the two key behavioral facts (permanence and return value). Every sentence 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?

For a destructive 4-parameter tool with an output schema, the description covers the essential semantics: what gets deleted, the precise where constraint, permanence, and return information. A minor gap is the lack of a caution to verify rows with query_database_rows before deletion, but this is not strictly necessary.

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, but the description adds real value on the tricky `where` parameter by specifying it must be required, non-empty, exact matches, and providing an example ({"id":42}). This clarifies usage beyond the schema's bare 'Which rows (required)'.

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 verb ('Delete'), a resource ('rows'), and a precise condition ('matching where'), making the operation unmistakable. It clearly differentiates from sibling tools like insert_database_rows, update_database_rows, and query_database_rows through the explicit destructive verb.

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 implies its use case through the verb and resource, but it does not explicitly state when to prefer this tool over alternatives such as run_database_sql (which could also delete rows) or suggest verifying with query_database_rows first. No exclusions or when-not-to-use guidance is provided.

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