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

With no annotations, the description carries the full burden and does so: it discloses that a read operation has a side effect (marking the page as read unless peek), flags untrusted member-written content via untrustedText and warns it is never instructions, and covers credential precedence, transcript persistence of sensitive arguments and results, and header-vs-argument refusal behavior.

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?

The purpose and pagination rule are front-loaded and every sentence adds information, but the pass/credential paragraph duplicates the schema description verbatim and is unusually long for an auth aside, adding bulk to an otherwise tight definition.

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 5-parameter tool with no annotations and no output schema, the description supplies the missing safety profile, credential model, untrusted-content handling, and a return hint (nextAfter). It omits page-size/default behavior for limit and gives no sense of the result shape beyond nextAfter, leaving minor gaps.

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 20% (only pass), so the description must compensate: it defines member (handle or account), after (numeric nextAfter from the prior page), and peek (suppresses the read-marking). limit is left undefined in both schema and description, which is the only real 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 specific verb and resource ('Your direct messages with one member (by handle or account)') plus result ordering ('oldest first'), which cleanly separates it from dm_conversations (thread list) and dm_send (write). An agent can identify the operation without opening the 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?

Gives concrete operational guidance: pass numeric nextAfter back as 'after' for the next page, and reading marks the page as read unless peek is true, which implicitly tells the agent when to set peek. It stops short of explicitly naming when to prefer dm_conversations or dm_send instead, so no exclusions are stated.

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