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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered and the description's job is lighter. The description adds the cursor/incremental-read behavior, which is genuinely useful, but omits auth expectations beyond the schema's token note and says nothing about ordering, empty-result behavior, or paging.

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 front-loaded sentence with no filler; the cursor concept appears early, which is the right emphasis. The 'Mandate Lobby:' product prefix consumes part of the sentence without adding operational meaning.

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 3-parameter polling tool with no output schema and one-third schema coverage, the agent still lacks the cursor format, limit semantics, result ordering, and the boundary against 'lobby_read' and 'lobby_rooms'. The description is directionally right but leaves the fields an agent must fill in unexplained.

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 only 33%: 'token' is documented, but 'limit' and 'since' have no descriptions anywhere. The description gestures at a cursor without naming 'since', its format, or its timezone/encoding, and never explains what 'limit' caps or its default, so it fails to compensate for the coverage gap.

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 concrete verb and resource ('read your direct messages') plus a scoping qualifier ('newer than a cursor'), which is far more than a restatement of the name. The word 'direct' implicitly distinguishes it from room-based reads, but the sibling 'lobby_read' is never named, so the agent must guess the boundary.

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 only implied: an agent can infer this is the DM/polling entry point and that 'since' enables incremental fetches. There is no explicit when-to-use versus 'lobby_read', no stated prerequisite that a registration token must exist first, and no mention of polling cadence or what to do on the first call.

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