Mark Read

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

No annotations are provided, so the description carries the full burden. It does disclose the key non-obvious behavior: the conversation is marked read and no reply is sent, which matters given the send_reply sibling. It says nothing about idempotency, required permissions, or whether other conversation state changes.

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, front-loaded with the action and its key constraint, then the rationale. No wasted words and the intent is clear on first read.

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?

An output schema exists, so return values need no explanation, and the tool's scope is a single-parameter state change. The description covers purpose and usage well; only permission requirements and idempotency are unaddressed, which are minor for this small a mutation.

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 would need to compensate, but it never mentions the single conversation_id parameter. The parameter name is largely self-explanatory and typed as string, so the practical gap is small, but the description adds no meaning beyond the schema.

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 ('Mark a conversation as read') and immediately adds the disambiguating constraint 'without replying', which cleanly separates it from the send_reply sibling. An agent can route to it 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 usage context ('auto-replies and anything already handled elsewhere') and the goal it serves (keeping the unread queue a real to-do list). It implies the alternative by negation ('without replying') but never names send_reply explicitly as the contrasting tool.

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