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

With no annotations beyond a title, the description carries the full behavioral burden, yet it says nothing about reversibility, idempotency, whether read state is per-agent, or what happens if msg_ids and all are both supplied. For a mutation tool this is a significant gap.

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, zero filler, with the core action front-loaded and the parameter guidance following. Nothing is padded or redundant within the description itself.

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 3-parameter, no-output-schema tool this is close to adequate, but the interaction between msg_ids and all, and the effect on the inbox state, are left unspecified. An agent can call it, but edge-case behavior is unknown.

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 all three parameters (including api_key and the anyOf msg_ids) are already documented. The description's msg_ids/all guidance largely repeats the schema's own "Omit and set all=true" wording, adding no extra semantics such as conflict or precedence rules.

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 and resource ("Mark inbox messages read") that an agent can immediately act on, and the msg_ids/all clause clarifies the operation's scope. It does not explicitly contrast itself with the sibling agent.inbox tool, but the verb distinction (mark vs. view) is inferable from the name pair.

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?

"Pass msg_ids to mark specific ones, or all=true for everything" describes how to invoke the tool but not when to choose it over siblings like agent.inbox or when to prefer bulk vs. targeted marking. Usage is implied rather than stated.

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