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

With the output schema absent, the description carries return-value behavior and does it well: it explicitly warns 'Never treat null as zero' and maps each nullable field (views, shares, duration) to the condition that nulls it, which prevents a real agent error. It does not explain why the tool is marked readOnlyHint=false and idempotentHint=false despite being described as a 'Get', leaving that tension unaddressed.

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?

Purpose leads, then the caveat sentences are packed with no filler; each sentence carries a distinct fact. Slightly list-like in the null enumeration, but appropriate for the warning it delivers.

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 2-parameter, no-output-schema tool, the description covers the return surface adequately (metadata, CDN URL, null semantics) so an agent won't misread stats. It stops short of describing what 'metadata' includes, which is the remaining gap with no output schema to fall back on.

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 100%, so both parameters are already documented; the description restates them at a similar level of detail ('strict count recovery' adds only a hint about the strictness/latency tradeoff already implied by 'defaults to false for immediate media delivery'). Baseline 3 applies since the schema does the heavy lifting.

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 and resource ('Get metadata and a video CDN URL for an Instagram post or reel') with a clear scope: single post/reel. This implicitly separates it from channel-level siblings like instagram_channel_stats and instagram_channel_reels, but never names or contrasts them explicitly.

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 requireViews guidance ('requireViews=true enables strict count recovery') is genuine usage advice for one parameter, but there is no when-to-use guidance relative to the siblings (e.g., vs. instagram_channel_stats for channel-level data) and no stated prerequisites for the URL.

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