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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful context beyond that: the output is "computed"/derived rather than raw, and best practice is to pair it with get_alerts in the same session. No rate limits, cost, or data freshness window disclosed.

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?

Three short sentences, zero filler, and the deliverable is front-loaded before the usage trigger. The trailing rationale ("so a falling account is flagged") justifies the companion call rather than padding.

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?

No output schema exists, but the description enumerates the return components well enough to set expectations. Combined with only two parameters (one required) and full annotation coverage, an agent has what it needs to call it correctly. A note on the projection horizon or period-dependent behavior would close the remaining gap.

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%, with the period enum and username format fully documented in the schema itself (including "without @"). The description adds no parameter-level detail such as how the chosen period affects projection confidence or output granularity. Baseline 3 is correct when 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?

Specific verb + resource ("Get a computed growth summary") followed by the three content components it returns: follower projections, engagement trends, posting frequency. That distinguishes it from raw-stats siblings like get_account_stats. It never explicitly names sibling alternatives (e.g., get_tiktok_growth_summary for the TikTok variant), so it stops short of a 5.

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 concrete triggering questions ("growth trajectory, future follower estimates, or overall account health"), which is real when-to-use guidance rather than vague targeting. It also prescribes a companion call — "Call get_alerts for the same account too" — a genuine cross-tool workflow instruction. It lacks explicit when-not guidance or a named alternative to avoid.

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