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

Goes well beyond the readOnly/idempotent annotations: it discloses the default-account fallback when accountId is omitted, that `handle` in the response identifies which account was used, and that `available: false` signals the network returned no data (common for small accounts and unsupported networks). These are exactly the edge cases an agent would otherwise misread as an error.

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 resource and its scope, then packs the defaulting rule, the empty-data sentinel, and the alternative tool into short clauses with no filler. Every sentence carries information an agent needs.

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?

With no output schema, the description compensates by naming the returned dimensions and their shape (label/value), plus the `available` flag. 'sorted' is not specified by which key, and geography is capped at top 10 without saying so for age/gender — small but real ambiguities.

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 already 100%, so the schema documents both params, but the description still adds the consequence of omitting accountId (first Instagram or YouTube account of the workspace) and ties it to a response field. Workspace resolution logic is left to the schema.

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?

Opens with a specific verb+resource ('Read audience demographics of one Instagram or YouTube account') and enumerates exactly what is returned: age, gender, top 10 countries, top 10 cities, label/value pairs. It is immediately distinguishable from analytics-style siblings such as get_analytics or get_top_posts.

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?

Explicitly routes the agent to get_follower_growth for follower numbers over time, which is the closest overlapping need. It also says which networks this applies to. What it lacks is guidance against other analytics siblings (get_analytics, get_engagement_trend), which an agent must infer.

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