What actually works: by hour, kind, tag; OON-entry rate; goals; advice

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description doesn't need to repeat safety. It adds useful behavioral context: it's free and local, aggregates own posts, and depends on snapshot freshness (refresh with post_performance). This goes beyond annotations by explaining the data dependency and how to improve accuracy.

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 a single, dense paragraph that front-loads the core value ('Free, local. Aggregates...') and then lists metrics. It's long but every sentence adds value; the list of metrics is necessary to convey the tool's scope. Could be slightly more structured with bullet points, but it's acceptable for a description.

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 (many metrics, dependency on snapshots and tags), the description covers the key aspects: what it does, how to improve it (tag posts, snapshot), and the optional 'days' parameter. No output schema exists, but the description lists the outputs (metrics) in detail, so the agent knows what to expect. It doesn't mention edge cases like empty data, but that's minor.

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% (the only parameter 'days' has a description: 'Window (default 30).'). The description doesn't add much beyond that, but it does mention 'best posting hours' and 'top posts' which relate to the time window. Baseline 3 is appropriate since the schema already documents the parameter adequately.

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 clearly states the tool aggregates user's own posts and metric snapshots into business-relevant analytics, listing specific metrics (originals/replies/threads, OON-entry rate, engagement by kind/tag, best hours, etc.). It distinguishes from siblings by emphasizing 'free, local' aggregation and the need to refresh with post_performance, which is unique among the listed tools.

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 implies when to use it (to get business-watching numbers) and mentions a dependency on post_performance for refreshing snapshots, plus tagging posts for sharper insights. It doesn't explicitly state when not to use it or name alternatives, but the context is clear enough for an agent to decide.

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