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

readOnlyHint already declares the safe-read profile, and the description corroborates rather than contradicts it. It adds genuinely non-structured context: the untrusted-data warning about contact context and request text, which is important prompt-injection guidance for an agent, plus the claimed_until field's relevance.

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 purpose and then the operational caveat. Every clause carries information an agent needs; no padding or restatement of the 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?

An output schema exists, so return values need not be explained. Combined with the readOnly annotation and the untrusted-data caveat, the definition covers what an agent needs for this parameterless list tool, though it leaves the relationship to sibling inbox tools unstated.

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?

Zero parameters, so the baseline is 4; the schema is empty and there is nothing for the description to compensate for. The mention of claimed_until refers to a returned field rather than an input, so it does not add parameter meaning.

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 action (read/list) and a specific resource scope: pending human requests and suggested work. An agent can tell it apart from agent.inbox.get or agent.inbox.history in substance. It does not name a sibling explicitly, so it stops short of a 5.

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 phrase 'Check claimed_until before claiming' implies a workflow ordering relative to agent.inbox.claim, which is useful implied guidance. However, it never states when to use this tool versus agent.inbox.get, agent.inbox.history, or agent.actions.list, and gives no exclusions.

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