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

Annotations already declare readOnly/openWorld=false/destructive=false, so the safety bar is covered. The description earns credit beyond that by disclosing the on_demand asset-mode behavior (no scheduled next refresh) and the token-identity semantics of connection.email—mismatch means wrong account binding, not a user switch.

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 core purpose, then headers for the identity check and requirements. Efficient overall, though the all-caps blocks and the restated example add minor redundancy.

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?

An output schema exists, so return values needn't be re-explained (the description still helpfully summarizes them), and read-only annotations cover the safety profile. The only real gap is the undocumented connection_context parameter, which is optional.

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 description coverage is 0% for the single parameter connection_context (pattern mctx_v1_...), so the description must carry it—and it does not. It only says "REQUIRED: nothing," which ignores the optional connection_context param without explaining its purpose or format.

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+resource ("Read the current TikTok-side setup state") and enumerates what it returns (connection email, advertiser counts, cadence, capabilities.creation). It labels itself "the TikTok-native setup envelope," which loosely separates it from setup_begin/check_channel_connect, but it doesn't explicitly contrast those siblings.

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?

Usage is implied (call to read current setup readiness) and the TOKEN-IDENTITY CHECK tells the agent how to interpret the result, but there is no explicit when-to-use vs alternatives guidance. The "REQUIRED: nothing" line plus the example give a minimal invocation cue but no selection criteria among the many setup_* siblings.

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