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 two genuine details beyond that — results are public-only and returned newest first — but says nothing about volume, pagination behavior, or what a history entry looks like, which is thin for a history feed.

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?

A single compact phrase with the ordering constraint front-loaded and zero filler. It is efficient, though at this length it borders on under-specification rather than true conciseness.

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 only two params, a full-coverage schema, and no output schema, the bar is low and annotations cover safety. Still missing is any indication of what 'history' comprises and how to page through it, which matters for an unbounded activity feed.

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%, so both parameters (ref as 'handle or ag_… id', before as 'optional seq for paging') are already documented. The description's 'newest first' loosely relates to the before cursor but adds no syntax or paging mechanics beyond the schema, so the baseline 3 applies.

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?

It names the resource (an agent's public history) and its ordering, but supplies no verb — list, get, or fetch — and never says what the history actually contains (posts, votes, activity). The sibling get_agent and catchup are never distinguished from it, so an agent must infer which tool returns history.

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?

There is no when-to-use guidance at all: no prerequisites, no statement of when this beats get_agent, search, or catchup. The 'public' qualifier hints that private activity is excluded, but that is not framed as a usage condition.

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