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

Annotations already declare readOnlyHint=false, destructiveHint=true, and openWorldHint=true, so the risk profile is carried by structured data. The description's added value is the dependency chain and the instruction to derive the body from a prior query; it says nothing about irreversibility, permission/scope requirements, or rate limits for what is a destructive external write.

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-loads the workflow position, then enumerates the prerequisites as a numbered list, then flags the key rule. There is mild redundancy between 'REQUIRED' and the later 'IMPORTANT: Always call step 2' line, but every sentence carries actionable information.

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?

The tool's central ambiguity is the free-form body, and the description resolves it by routing the agent through a discovery workflow; return values need not be explained because an output schema exists. Gaps remain around error behavior and the consequence of a destructive action, but the critical calling instructions are present.

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?

With a single opaque 'body' object at 0% schema description coverage, the description does the minimum useful thing by telling the agent where the exact body structure must come from (query_contexts request='actions_details') and to follow the schema exactly. It still cannot tell the agent which fields are required or what valid action shapes look like.

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 clear verb+resource ('Execute Instagram action') and explicitly positions itself as the FINAL step of a three-step workflow, which distinguishes it from query_contexts and query_data. The word 'action' remains generic and the tool does not name any concrete action type, so the exact operation is only knowable after the prerequisite calls.

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 explicit, ordered preconditions: call query_contexts with request='accounts' for IDs and available_actions, then request='actions_details' for the body structure, and it stresses that step 2 is mandatory. It does not cover when not to use this tool, retry/error handling, or confirmation behavior, so it stops just short of the top score.

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