Run a database modification

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

The description extensively discloses behavioral traits beyond annotations: no snapshot/rollback for database writes, the need for confirm, the guard against unscoped writes, and the best-effort classifier that fails closed. This aligns with annotations (destructiveHint=true, readOnlyHint=false) and adds crucial risk context an agent needs.

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 compact but dense, with the primary action stated first, followed by critical constraints and parameter usage. Every sentence contributes meaningful information (prerequisites, safety checks, parameter formats). It's not bloated, but slightly longer than necessary; still excellent.

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?

Given the tool's complexity (7 params, safety guards, no output schema), the description covers all essential aspects: the operation, prerequisites, guard behavior, parameter passing, and failure modes. An agent has enough information to invoke it correctly and understand risks without further reference.

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% with descriptions for all params. The description adds value by explaining the semantics: params is a { name: value } map, params_list is for bulk rows, confirm guards against accidental writes, and allow_unfiltered is required for mass writes. This enriches the structured schema details.

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 (execute) and resource (saved db_modification), and clarifies it's for INSERT/UPDATE/DELETE operations. It clearly distinguishes from siblings like execute_query (which likely reads) by emphasizing it writes to a database, and the 'by name' scoping differentiates from other modification tools.

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?

Explicit usage conditions are given: requires data writes enabled (PORTAL_ALLOW_DATA_WRITES=1), confirm=true, and describes when it refuses to run (unscoped mass writes without allow_unfiltered=true). While it doesn't name alternative tools, it provides clear prerequisites and boundary conditions, making it good but not perfect.

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