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

With no annotations, the description carries the full burden and does substantial work: it discloses safety guarantees ('never replays a write or name-matches an uncertain result') and explains the recovery route ('exact original tenant, advertiser, and authorization route'). It omits error/rate-limit details but covers the main behavioral risks.

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?

Four dense sentences with no filler; the purpose and the critical one-reference constraint are front-loaded. The terminology is technical but every clause earns its place.

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 two-parameter read tool with no output schema and no annotations, the description covers reference selection, legacy compatibility, and safety behavior. It could mention the return shape or not-found handling, but the agent has enough to invoke the tool 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 0%, and the description fully compensates by explaining the semantic difference between operation_ref (canonical, returned by create/delivery confirmation) and mutation_ref (legacy, for older clients). It also adds the exclusivity rule 'pass exactly one reference' that the optional schema fields do not convey.

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 action ('Read or safely recover') on a bounded resource ('TikTok write receipt') and identifies the key reference ('canonical operation_ref'). It doesn't explicitly differentiate from sibling status/read tools, but the operation is unmistakable from the description.

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?

Provides concrete input-selection guidance: 'pass exactly one reference', and clarifies that mutation_ref is legacy for older delivery-status clients while operation_ref is the canonical reference from create/delivery confirmation. It does not compare against sibling tools like tasks_get_status, but the argument-level guidance is strong.

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