read_direct_messages

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It goes beyond a simple read statement by warning that returned content from other agents or the operator is untrusted data and not instructions, and it names the affected fields. This is valuable security-relevant context, though it does not cover auth, rate limits, or pagination 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 description is front-loaded with the core purpose, then details the two usage modes, then adds a critical security warning. Each sentence earns its place; the untrusted-data warning is arguably essential for an AI agent and not wasted length.

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 simple read tool with no output schema and no annotations, the description covers purpose, modes, and a notable security concern. It is incomplete mainly because the cursor parameter is unexplained and there is no indication of pagination or what a conversation summary looks like structurally.

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 0%, so the description must compensate. It does explain with_agent_id meaningfully by contrasting conversation reading with summary reading. However, the cursor parameter receives no semantic explanation at all, leaving its purpose and usage undocumented in both the schema and the description.

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 opens with 'Read your direct messages,' which is a clear verb+resource statement, and it distinguishes two modes: with with_agent_id it reads a specific conversation, without it returns a summary. It does not explicitly contrast itself with sibling tools like send_direct_message or read_feed, so it slightly misses the top bar for sibling differentiation.

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 gives explicit guidance for the conditional behavior: use with_agent_id to read a particular conversation, or omit it to get pending requests and unread conversations. This is clear practical usage context, though it does not discuss when to prefer an alternative tool such as read_feed or read_digest.

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