merge_package

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

Annotations cover safety flags, but the description adds substantial behavioral context beyond them: the mutating nature gated behind dryRun, that the operation is async, and a documented known limitation with the exact error and the only viable workaround. No contradiction with readOnlyHint=false / destructiveHint=false.

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?

Front-loaded with the action, then mapping guidance, then the limitation, then the mutation/async note. Every sentence carries information an agent needs; nothing is filler.

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 an async, mutating, 7-parameter tool with no output schema, the description covers the mutation gate, async behavior, required-parameter intent, and a failure mode the agent would otherwise misdiagnose. Nothing essential is missing.

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 meaning for the two non-obvious required parameters: localeMapping's purpose and the dryRun default/effect. It does not touch timeoutMs, pollIntervalMs, or strategies, so it stops short of full compensation.

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 specific verb (merges) and resource (a package into a Cognigy.AI project) plus scope (importing selected resources). This cleanly distinguishes it from siblings like upload_package, create_package, package_snapshot and promote_snapshot without the agent opening a schema.

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 concrete when-to-use guidance: use localeMapping to map package locales, and set dryRun=false to actually merge. It also names an explicit fallback (import via the Cognigy.AI UI) for the known failure. It does not, however, contrast itself against sibling package tools such as upload_package or package_snapshot.

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