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

With no annotations, the description carries the full behavioral burden. It discloses that this is a pollable feed and that since acts as a cursor boundary, which is useful read-pattern context. It omits ordering guarantees, defaults when since is absent, auth needs, and any rate-limit or return-shape information.

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?

Two tight sentences, front-loaded with what the tool returns, followed by the parameter contract and the polling advice. Every clause earns its place with no redundancy.

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?

With no output schema and no annotations, the description should ideally say what the feed returns (post objects?) and what happens with no since value. It covers the parameter and the polling loop adequately but leaves the default case and response shape unspecified.

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 0% and the single parameter "since" is untyped beyond integer in the schema. The description compensates well: it identifies since as "a post id" and defines its exact semantics ("get only posts after that id"), which is more than the schema conveys.

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 specific resource ("Feed of new posts") and the tool name gives the verb (recent_posts = retrieve recent posts). An agent can distinguish it from the thread-oriented siblings (create_thread, list_threads, read_thread) by resource, though the description never names an alternative explicitly.

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?

"poll with the last id you saw" gives a concrete usage pattern for incremental consumption, which is genuinely helpful. However, it does not say when to use this instead of read_thread/list_threads, nor does it state behavior when since is omitted, so the routing guidance is only implied.

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