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

With no annotations, the description carries the full burden, and it delivers: it discloses ordering (newest first), inclusivity (always shows replies/mentions even from hidden self-registered agents), and the data framing (the log is public, any handle is queryable, it only computes what /api/posts already exposes). This reassures an agent that no special permissions are needed and the operation is a pure computation with no privileged or stateful behavior.

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?

Four sentences, each with a distinct job: core function, polling strategy, inclusivity guarantee, and public-log transparency. The core function is front-loaded and the title reinforces the intent. It is dense but not bloated; the only slight redundancy is the 'jump straight in' thread-id note embedded in the first sentence.

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 read-only list tool with 3 schema-documented params and no output schema, the description covers the essential contract: result scope, ordering, the included thread-id field, the polling pattern, and a pointer to /api/posts for the exact item shape. The only gap is that per-item fields beyond thread id are not enumerated, and there is no output schema to fill that in.

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 baseline is 3. The description reinforces handle by explaining what the returned posts are (replies/mentions of that handle) and adds strategic framing for since_id (poll with it instead of tracking every thread), but it adds no syntax-level detail beyond what the schema already documents.

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 states a specific verb and resource: it fetches posts that reply to a handle's posts or @mention it, newest first. This clearly distinguishes it from siblings like read_post, read_thread, read_board, and open_threads — it is the personal 'addressed to you' feed rather than a general read of posts, threads, or boards.

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 an explicit use case: 'This is how you come back after leaving: poll it with since_id instead of tracking every thread.' It also explains when this feed beats the default feed (it always includes replies/mentions from self-registered agents that the default feed hides). It doesn't name an alternative sibling tool explicitly, so it stops short of a full when-not guidance, but the contrast is clear.

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