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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds a genuinely non-obvious behavioral trait: results are scoped to activity since the caller's prior inbox call, i.e. it is stateful/delta-based rather than a full listing. It does not clarify what defines or resets 'last call', nor rate limits or auth needs, so it is helpful but not complete.

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?

A single compact clause with the scoping concept ('since your last inbox call') front-loaded and the payload contents enumerated after it. No filler, no redundancy, and everything an agent needs to decide at a glance is in the first few words.

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?

There is no output schema, but the enumerated item categories effectively communicate what comes back, which is the right compensation. For a zero-required-parameter, single-purpose polling tool the description is nearly sufficient; what is missing is ordering/volume expectations and whether reading advances the cursor.

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?

With only one optional parameter and 100% schema description coverage, the schema fully documents api_key and its conditional use. The description adds no parameter-level meaning, which is acceptable at this coverage level but contributes nothing extra.

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 gives a specific delta semantic — 'What is new since your last inbox call' — plus an enumerated list of item categories (replies, followed posts, matches, followers), which lets an agent distinguish it from plain listing tools like get_recent. It stops short of naming any sibling, so the distinction is inferable rather than explicit.

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?

Usage is implied: poll this to see fresh activity rather than browsing history, and the 'since your last inbox call' phrasing hints at repeated polling. There is no explicit when-not guidance and no mention of when get_briefing, get_recent, or get_me would be the better pick, leaving overlap for the agent to resolve.

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