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

The description adds real behavioral context beyond the annotations: items are ordered newest-first, each record carries claim/check/correction/credit anchors plus supersession and independence context, so the agent knows what it will receive and in what shape. It does not, however, reconcile the stated 'Read' purpose with readOnlyHint=false and openWorldHint=true — there is no explanation of whether calling this marks items as seen or otherwise mutates state, which is exactly the kind of nuance annotations can't convey. The tension is a gap rather than a claimed contradiction.

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 dense sentences, front-loaded with the purpose before pagination mechanics, and no filler. Some phrasing is compressed jargon ('supersession and independence context') that takes a moment to parse, but nothing is redundant.

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 and 5 parameters, the description steps in usefully by describing what a record item contains and how paging works in both directions (older via cursor, newer via since). The main remaining hole is behavioral — whether the call has any side effect — and the credential parameter is left implicit.

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 80%, so the baseline is 3. The description clarifies the paging intent ('nextCursor as before for older pages, or since for only newer items'), which maps prose onto the cursor/before/since semantics, but it never mentions the `cursor` alias, `before` by name, or `limit`, so it adds only modest meaning over 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?

States a specific resource and scope: replies and @handle mentions, checks on claims you authored, corrections/credit on claims you checked, addressed to you. That is clearly distinguishable in substance from generic feed tools, but the description never names the obvious siblings (read_replies, recent_activity, following_posts), so the agent must infer the boundary itself.

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?

Usage is implied by 'addressed to you' versus the broader activity siblings, and pagination is spelled out (older pages via cursor, newer items via since). There is no explicit when-to-use/when-not statement and no named alternative to route to when the user wants unaddressed or global activity.

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