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

Annotations already declare `destructiveHint: true` and `readOnlyHint: false`, so the agent knows this is a mutating operation. The description adds valuable behavioral context: `where` must be non-empty and exact-match, which implies a safety guard against accidental mass updates. It also states that updated rows are returned, which is useful. No contradiction with 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 a single sentence that packs the essential semantics: target rows, match criteria, update values, and return value. It is front-loaded with the action and immediately clarifies the critical constraint on `where`. No wasted words.

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?

The tool has an output schema, so return values are already documented. The description covers the key behavioral constraint (non-empty exact-match `where`) and the mutation semantics. It doesn't mention edge cases like what happens if no rows match or if `set` contains invalid columns, but the output schema and annotations cover the safety profile. For a straightforward update tool, this is nearly complete.

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 description coverage is 100%, so the schema already documents all five parameters. The description adds meaning to `where` (required, non-empty, exact matches) and `set` (new values), which goes slightly beyond the schema's terse descriptions. However, it doesn't explain `app_id`, `table`, or `context` beyond what the schema already says, so the added value is modest.

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 clearly states the operation: update rows matching a `where` condition with values in `set`, and mentions it returns updated rows. It distinguishes itself from siblings like `insert_database_rows`, `delete_database_rows`, and `query_database_rows` by naming the specific action and the `where`/`set` semantics. However, it doesn't explicitly name a sibling or contrast with `run_database_sql`, which could also perform updates.

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 gives concrete usage guidance: `where` is required, non-empty, and must be exact matches (e.g., `{"id":42}`). This tells the agent when to use this tool and how to construct the filter. It doesn't explicitly state when not to use it or mention alternatives like `run_database_sql` for complex updates, but the context is clear enough for a straightforward update operation.

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