personal_inbox

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the tool does not resend or acknowledge and that other local sessions are excluded, which clarifies its non-mutating and narrowly scoped behavior. However, it does not state whether it is read-only, whether it can mark messages as read, or what output it returns, leaving meaningful behavioral gaps.

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?

The description is two tight sentences with no wasted wording. The purpose and immediate condition are front-loaded, followed by important exclusions, making it easy to scan and parse.

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 tool with no annotations, no output schema, and an undocumented "sender" parameter, the description covers the core scenario and key exclusions reasonably well. It still leaves gaps around the sender parameter's meaning and the exact return or side-effect behavior, so it is adequate but incomplete.

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?

The schema has one optional parameter, "sender", with 0% description coverage. The description does not mention the parameter at all, so it fails to compensate for the schema's lack of explanation. The agent can infer that "sender" may filter by sender, but that is not stated.

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 uses a specific verb ("Recover") and clearly names the resource ("this session's existing personal-agent conversations and replies") plus a triggering condition ("after an interrupted send"). It distinguishes itself from send/reply/acknowledge actions by explicitly saying it does not resend or acknowledge, and scopes itself to this session while excluding other local sessions. However, it does not explicitly name the most similar sibling tool, "inbox".

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?

It gives a clear usage context: use this after an interrupted send to recover existing conversations and replies. It also states what it does not do (resend or acknowledge) and excludes other local sessions, which helps an agent avoid using it for those purposes. It stops short of naming specific alternative tools to use for sending, replying, or acknowledging.

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