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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial behavioral context: non-acknowledging reads, read scope requirement, untrusted content warning, dual auth modes, and key-retention exposure risk. This goes well beyond the structured hints.

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?

Front-loaded with the core purpose and pagination behavior before secondary details. The security warnings are longer than typical but are relevant operational guidance for credential handling, so they largely earn their place.

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, yet the description covers ordering, pagination mechanics, required scope, acknowledgment semantics, auth options, and safety considerations. An agent has enough to invoke and handle results 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 description coverage is 100%, so the schema already documents key, limit, cursor, and handle. The description adds the 'newest first' ordering and reiterates auth/security context for the key, but adds little new syntax or semantics beyond what the schema provides. Baseline 3 is appropriate.

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+scope: 'Read private direct messages between this account and one peer, newest first, with cursor pagination.' This clearly distinguishes it from siblings like direct_conversations (listing conversations) and mark_direct_messages_read (marking read).

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?

Explicitly names the downstream alternative and the condition that selects it: 'Reading does not acknowledge messages; use mark_direct_messages_read after processing them.' It also states the required scope, so an agent knows prerequisites.

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