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

Annotations already cover the safety profile (readOnly=true, destructive=false), yet the description adds real behavioral content: union totals across the full window, per-identity baseline/current counts, identities and absolute/percentage change, explicit handling of selected zeros, unavailable identities, and undefined zero baselines. It also warns that sentiment is not inferred and collection coverage is not equalized — genuine caveats not derivable from annotations or schema.

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 trigger condition is front-loaded, followed by return contents, then caveats — a sensible order with no padding. The wording is dense and occasionally telegraphic ("zero baseline is undefined"; "full-window union totals"), which costs a little readability but every sentence carries distinct information.

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 correctly takes on the return-value burden and describes totals, per-identity counts, identities and change measures. For a tool whose two arguments are large nested filter objects, it could say more about how the two windows must be kept comparable and how paging behaves, but nothing an agent needs to avoid calling it wrongly 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?

The nested schema carries detailed descriptions for cursor, date bounds, ID sources and filter semantics, but the reported coverage signal is 0% for the top-level structure. The description clarifies that both periods should target the same assets/authors/topic and explains result semantics around zeros, but it adds no guidance on the many nested filter parameters (chain_ids, evidence_class, post_types) that an agent must populate. Baseline 3 reflects partial compensation rather than full coverage.

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 opening sentence gives a specific verb (compare), a specific resource (discussion volume / activity), and the scope (two periods for the same assets, authors or topic). An agent can distinguish this from siblings like aggregate_posts or discover_activity without opening the schema, and the description also states what it does not do.

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?

"Use when comparing how discussion volume changed between two periods..." states the trigger condition clearly, and "Read posts separately to assess views" routes one adjacent need elsewhere. It stops short of naming concrete sibling tools (e.g. search_posts, aggregate_posts) or stating explicit when-not conditions, so it is strong context without full alternative mapping.

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