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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's job is to add behavior, and it does: results are default-filtered to unread and non-hidden changes, sorted newest-first, and include an unread count. It adds no note on pagination behavior beyond the cursor param or on cost/latency for large feeds.

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?

Two sentences, zero filler, with the scope-and-ordering definition front-loaded before the sibling routing. Every clause carries information the schema and annotations do not.

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?

For a five-param, all-optional list tool with no output schema, the description covers the filter defaults, ordering, and the presence of an unread count, which is enough to call it correctly. A brief note on paging through results or what a feed item contains 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: "changes they have not marked read" explains the default state that includeRead flips, and "the inbox the Monity Feed shows" frames the teamHidden default behind includeHidden. It adds nothing about limit/cursor/labelIds, though the schema already covers those well.

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 person's Monity feed: alerted changes they have not marked read, newest first, with the unread count" gives a specific resource, the default filter, the sort order, and the response payload in one clause. It also explicitly separates this tool from get_recent_changes, so an agent can pick between the two without opening a schema.

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?

It names the alternative (get_recent_changes) and the condition that selects it (a date-range report), which is exactly the routing an agent needs for the most likely confusion. It doesn't mention the adjacent inbox operations (mark_feed_read, hide_change, unhide_change) that act on this same feed, so the guidance is clear but not exhaustive.

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