mark_messages_read

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

With no annotations, the description carries the full burden and does add two useful facts: the operation is reversible and it needs no confirmation. It omits what happens with unknown or malformed message_ids, whether partial failures are reported, and whether any special permissions are required.

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?

Two short sentences, each earning its place, with the primary batch-read behavior front-loaded and the reverse mode and no-confirmation note following. There is no redundant restatement of the tool name.

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 two-parameter mutation with no annotations and no output schema, the description covers the essentials: batch scope, reversibility, and the flag's polarity. It is not fully complete because it never addresses return values, partial-failure behavior, or the relationship to the singular mark_read sibling.

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 0% and is_read is defined only by a boolean default, so the description's clarification that is_read=false marks messages unread (and by implication the default marks them read) adds genuine meaning. message_ids is a self-describing array, though the description does not say what format the IDs take.

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?

Uses a specific verb ("Mark ... read") plus resource (messages) and states the batch scope with "many messages ... in one call", which implicitly separates it from the singular sibling mark_read. It stops short of naming that sibling explicitly, so the differentiation is inferable rather than stated.

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?

It tells the agent how to flip the operation in reverse (is_read=false) and asserts that confirmation is unnecessary, which is real usage guidance. But with ~40 siblings including mark_read, move_messages and archive_messages, it never states when to prefer this over mark_read or what to do about IDs that come from search_message_ids.

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