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

Annotations already declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, so the safety profile is conveyed structurally. The description adds real context beyond that: execution is gated on prior discovery and the body must mirror a schema fetched at runtime rather than be invented. It does not say what a destructive action can irreversibly change or what happens on partial failure.

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 role and step number, then a numbered prerequisite list — easy to scan and act on. There is minor redundancy: the 'IMPORTANT' line repeats the step 2 instruction already given, and the 'xxxxxx' placeholders are expendable.

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, dynamically-schemed tool the critical unknown — how to build the body — is fully addressed, and an output schema exists so return values need not be described. Remaining gaps are effect disclosure (what the action mutates, reversibility, permission requirements) rather than invocation correctness.

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?

The single 'body' parameter is an open object with 0% schema coverage, so the schema itself gives no guidance. The description compensates as far as it can by naming the authoritative source for the body structure (actions_details with the actions from available_actions) and warning to follow it exactly — though it lists no actual fields and the placeholder 'xxxxxx' carries no information.

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+resource ('Execute TikTok Profile action') and frames it as the FINAL step 3 of a workflow, which distinguishes it from the sibling query_contexts (discovery) and query_data (reads). The word 'action' is left generic — the universe of action types is never enumerated, so the agent knows it executes something but not the domain of possible operations.

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?

Explicit when-to-use: only after completing two named query_contexts calls, with the exact request values ('accounts', 'actions_details') and the source of the action list (available_actions). It even states an imperative pre-condition ('Always call step 2 ... before executing'), leaving nothing to inference.

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