aism_migration_run

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

Annotations already declare destructive=true and openWorld=true, yet the description adds real value beyond them: which state is overwritten (target settings and previously migrated objects), that re-runs update rather than duplicate, that ID remapping and URL rewriting occur in finalize, and that users are not created. The write profile is fully consistent with the destructive annotation; there is minor tension between 're-running updates instead of duplicating' and idempotentHint=false, but that reflects source drift rather than a real contradiction.

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 phase list, then the resumability contract, then the overwrite/incremental caveats. Sentences are long and packed with clauses, but every one carries operational meaning and nothing is redundant.

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 12-parameter, destructive, no-output-schema, open-world tool, the description covers the resume protocol, overwrite semantics, status handling implications, and author policy. It could go further by signaling failure recovery or pointing to aism_migration_rollback, but it is complete enough to call correctly.

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, and the description goes beyond it by explaining the cursor loop contract ('until done is true') and the incremental semantics of modified_after, neither of which is inferable from the schema alone since there is no output schema. The author matching fallback chain (login, then email, then default_author) is reinforced rather than merely repeated.

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 (migrate) plus a precisely enumerated resource scope: terms, media, content types, comments, site settings, and a finalize remap pass. It is clearly distinguishable from siblings like aism_migration_plan, aism_migration_copy and aism_migration_export because it describes a full-site, resumable run against a configured target.

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 invocation guidance: call again with the returned cursor until done is true, and re-runs act as incremental sync when combined with modified_after. It does not explicitly route the agent between the sibling alternatives (plan vs copy vs run), but the runtime context it provides is clear.

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