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

Annotations already cover the read-only, non-destructive, closed-world profile, so the description earns credit for adding non-obvious behavior: conversations whose private source access changed return only 'safe locked metadata,' which explains why a listed row may be sparse. That is genuine context an agent cannot infer from the schema or annotations.

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 short sentences with no padding, and the core action is front-loaded. 'Person only' is telegraphic to the point of ambiguity, but it is not wasted space.

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?

An output schema exists, so return values need no explanation, but the description leaves the pagination contract (limit bounds, cursor lifecycle) unstated even though the regex schema text hints that 'limit counts rows read; an empty page with has_more true means keep paging.' For a three-parameter paging tool with partial schema coverage, that gap matters.

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 only 33% — regex is documented exhaustively, but limit and cursor have no descriptions at all. The description compensates only weakly: 'Page' hints at cursor/limit pagination but says nothing about the 50-row cap, cursor acquisition, or ordering, leaving two of three parameters undocumented in both places.

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 uses a specific verb ('Page') on a specific resource ('your conversations with the O++ assistant') and scopes it to 'across supported clients,' which clearly separates it from the singular conversation_get sibling. It stops short of naming that sibling, so differentiation is implied rather than stated.

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?

'Person only' is a real usage prerequisite that tells the agent this tool is not available to agent actors, and 'Page your conversations' implies the list-then-fetch pattern. However, it never states when to use this versus conversation_get, nor what happens when no filter is supplied.

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