mark_read

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

The description discloses a key behavioral trait: 'Affects unread state across all your linked devices.' This is valuable beyond the annotations (none provided). However, it does not mention reversibility, required permissions, or potential side effects (e.g., notifications). The transparency is moderate.

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 sentences that are front-loaded with the core purpose. Every word adds value; no fluff. Ideal conciseness for a simple tool.

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?

Given the existence of an output schema, the description does not need to detail return values. It explains the main action and ts usage, but leaves out details about the 'channel' parameter format, the optional 'workspace' parameter, and any prerequisites or errors. Adequate but not fully complete.

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?

With 0% schema description coverage, the description must compensate. It adds meaning for 'ts' by specifying it should be the most recent message ts. For 'channel', the resource is implied. 'workspace' is not explained. Overall, partial but incomplete guidance.

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 clearly states the verb ('Mark') and resource ('a channel') with a specific parameter ('up to a given message ts'). It distinguishes from sibling tools like read_channel, which likely retrieve messages without modifying unread state. The purpose is unambiguous.

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 provides guidance on how to set the 'ts' parameter ('Use the ts of the most recent message you've read'), but does not explicitly state when to use this tool over alternatives like read_channel, nor does it mention when not to use it. Some implicit context is present, but it lacks explicit usage boundaries.

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