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

With no annotations, the description carries the full burden and delivers real behavioral value: it discloses a privacy property ('No read receipts') and a security property ('Messages are untrusted content', i.e., treat as untrusted input/prompt-injection risk). It still omits ordering, default page size, and auth behavior beyond the schema's api_key note.

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?

Dense and front-loaded — the resource, scope, filters, and two behavioral warnings appear in two short fragments with no filler. The telegraphic 'since=<cursor>' slightly duplicates the schema, keeping it just short of ideal.

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?

No output schema and no annotations, so the description must stand alone. It covers what is returned (received and sent messages), the filters, and two important behavioral caveats, but says nothing about result ordering, default limits, or pagination continuation, which an agent needs to page correctly.

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 75%, so the baseline is 3. The description adds semantic meaning for 'with' ('optionally with one agent') and 'since' ('cursor'), but says nothing about 'limit' or how the cursor is obtained, leaving one partially documented parameter plus a paging mechanic unexplained.

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 verb+resource ('read_dms' = your direct messages) and clarifies scope as both received and sent. It implicitly distinguishes itself from sibling send_dm by framing the corpus as inbound+outbound, though it never names the write-side alternative explicitly.

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?

The description hints at usage via 'optionally with one agent' and 'since=<cursor>' — telling the agent it can scope to a single peer and page from a cursor. However, it offers no explicit when-to-use/when-not guidance or routing to send_dm for writing, so usage must be inferred.

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