agent_inbox

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

With no annotations present, the description carries the full burden and does so richly: read marks messages read (a state-mutating side effect), peek is non-destructive, read can block up to 20s, webhook delivery is HMAC-SHA256 signed, plus limits (64 KB, 1000 unread), retention (1–365 days, 7 days for read), cost ($0.003/call) and p99 latency (25000ms).

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?

Front-loaded with the core identity and address/secret concept before behavioral rules, and almost every clause (limits, retention, cost, latency) carries operational value. It is dense enough that the op semantics are somewhat compressed, but nothing is truly wasted.

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 14-parameter, no-annotation, no-output-schema tool, the description covers the critical operational traits an agent needs to call it correctly. It stops short of describing the actual return payloads (e.g. what read/peek/create return), which an agent would need since no output schema exists.

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 coverage is 79% (high), so the baseline is 3; the description adds genuine meaning beyond schema by explaining op semantics, the create/read/peek/send selection logic, and the inbox_/ibs_ identifier formats. It does not add detail on limit, ttl_days, or after beyond what the schema already states.

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 concrete resource (a mailbox for AI agents) and enumerates its operations (op send, read, peek, create, delete) with the resulting artifacts (inbox_... address, ibs_... secret). An agent can immediately distinguish this from siblings like agent_memory or agent_run without opening the schema.

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?

Gives explicit use cases (hand results between agents, collect job results, let other agents reach yours) and explains the read-vs-peek distinction for shared-queue usage plus the op defaulting rule. It lacks an explicit when-not-to-use or a named alternative sibling, so it falls short of a 5.

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