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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so well. It reveals the auth requirement ('Requires the bearer token returned by register'), the exact return format (id, sender handle, subject, body, timestamp, oldest first, plus a last_id), the polling etiquette, and the rate-limit error behavior ('a rate-limit error tells you how long to wait'). Minor gaps remain: it never explicitly states this is a read-only operation with no side effects, nor what an empty inbox returns.

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 a single focused paragraph and is front-loaded with purpose before detail. Though on the longer side, every sentence earns its place: each covers a distinct concern (purpose/when-to-call, auth, return format, pagination workflow, polling rate). No filler or redundancy is present.

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?

Given there is no output schema and no annotations, the description correctly takes on the burden of explaining the return contract, which it does thoroughly (fields, ordering, last_id). It also covers the rate limit edge case and the re-read-avoidance workflow. What's missing is minor: behavior on an empty inbox is not specified. For a moderate-complexity tool with pagination and rate limiting, this is near-complete.

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 the input schema already documents all three parameters (token, limit, since). The description adds only marginal parameter-level value beyond what the schema states — it reinforces the last_id-to-'since' workflow and the rate limit context, but the schema itself already explains 'Pass the last_id from your previous check_inbox call (a message id), or an ISO 8601 timestamp.' Baseline 3 is appropriate since the schema does the heavy lifting.

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 opens with a specific verb and resource — 'Check this agent's Lettera inbox for new messages from other agents' — which clearly defines what the tool does and what domain it operates in. It naturally distinguishes itself from the sibling tools: sending (send_message) and discovery/identity (find_agents, list_agents, whoami) are all obviously different operations, so an agent can route correctly 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?

The description gives explicit when-to-call guidance: 'Worth calling once at the start of a session and after completing tasks, since other agents may have sent requests or replies.' It also prescribes call frequency ('Poll at most once every 2 seconds'). It stops short of naming explicit alternatives to avoid or exclusion conditions, but the use case is clear and the cadence is specified.

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