Delete Metadata Record

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

Goes well beyond the annotations (destructiveHint=true, openWorld=true): it discloses that the delete is captured as a DELETE in a named update set and read back, that committing that set propagates the removal to other instances that already have the record, and that the call refuses protected files, platform schema tables, and ACL records. The additional note about refusing code-bearing writes without script permission is real behavioral context an agent could not infer from structured fields.

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?

Purpose is front-loaded, but the body is dense and repetitive: 'Only when the user asked for the delete' partly restates the first sentence, and the phrase 'Writes through the record's form' is confusing for a delete operation. Several clauses about code-writing refusal read as boilerplate carried over rather than delete-specific information.

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, ten-parameter mutation with no output schema, the description covers side effects, cross-instance propagation, refused targets, and update-set verification requirements. It stops short of explaining failure behavior or what the read-back yields, but the essentials for safe invocation are present.

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 schema already documents all ten parameters including the confirm_table/confirm_sys_id duplicate guards. The description only echoes the concepts of named application and update set without adding format or constraint detail beyond the schema, so baseline 3 applies.

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?

States a concrete verb and resource (delete an application metadata record via the platform's Delete) and immediately distinguishes it from sibling surfaces by naming the ACL tools for access-control records. An agent can tell this apart from query_delete_records or update_metadata_record by the singled-record framing and the update-set capture.

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?

Gives an explicit gating condition ('Only when the user asked for the delete') and an explicit exclusion with a redirect ('access controls (use the ACL tools)'). It does not contrast with the bulk query_delete_records path, so the alternative-routing is incomplete, but the when-to-use signal is clear.

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