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 usefully disclose the bulk-by-default behavior (omitting message_ids marks everything visible), which is the most important risk to flag; however it says nothing about permanence/reversibility, whether the change is scoped per-agent, or permission requirements.

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, the core action first and the parameter default second. No filler for a simple mutation 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?

An output schema exists so return values need not be covered, and the mutation's default scope is explained. But for a write tool with zero annotations, leaving the `agent` parameter and the permanence of the read-state change unexplained is a real gap.

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%, and only message_ids gets any semantic help (the null/omitted case means all visible). The `agent` parameter — critical in a multi-agent toolset with whoami/list_agents siblings — is completely undocumented in both schema and description, and message_ids' element format is left to 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 messages as read'), so the agent knows exactly what operation it performs. It does not explicitly contrast with the obvious sibling read_inbox, so an agent must infer the pairing from names alone.

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 second sentence defines a meaningful usage branch: omit message_ids to mark all visible messages. That is real conditional guidance, but there is no when-not-to-use, no mention of read_inbox or other siblings, and no statement of who 'visible' applies to.

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