instagram_prepare_dm

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial behavioral context: it emphasizes 'It only gathers context. Nothing is sent until instagram_send_direct_message is called, which is deliberate: the draft should be shown to you first.' It also discloses the disambiguation behavior ('If the person is ambiguous it returns the candidates instead of guessing') and details the output shape. This goes well beyond the annotations.

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?

The description is structured with a clear opening summary, then usage context, behavior, and structured Args/Returns sections. It's informative without being excessively verbose. The most critical information (not sending, disambiguation) is front-loaded. It could be slightly more concise in the Returns section, but the structure is effective for a complex tool.

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?

Given the tool's complexity and the presence of an output schema, the description is remarkably complete. It explains the two possible return shapes (needs_disambiguation vs. the full context object) which goes beyond the schema's structured definition. It covers parameter semantics, usage context, and behavioral expectations. Nothing an agent needs to correctly invoke and interpret the result is missing.

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 100%, so the schema already fully documents all three parameters. The description's Args section largely mirrors the schema, restating the same info (e.g., 'person: Name or handle of who to message'). It does add the note that person is omitted if thread_id is provided, but that is also implied in the schema for person. Since the schema carries the loading, the description adds minimal new semantic value, consistent with the baseline of 3.

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?

The description starts with a clear, specific statement: 'Get everything needed to draft a DM in one call: who, the conversation so far, and your voice.' It names the verb (get/prepare) and the resource (DM context) and explicitly contrasts with the sibling that sends (instagram_send_direct_message) by stating it only gathers context. This distinguishes it from the many related tools in the sibling list.

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?

The description explicitly says 'This is the tool to reach for when asked to write or reply to someone on Instagram.' It also clarifies that nothing is sent until instagram_send_direct_message is called, which guides the agent on sequencing and expectations. However, it does not explicitly mention when NOT to use it or compare with alternative context-gathering tools like instagram_get_direct_thread, so it's clear but not exhaustive.

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