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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. Beyond that, the description adds real behavioral facts: the hard cap of five results, that access is public with no enrollment, the snapshot-based delta behavior, and that follow-up requires operator opt-in. The only soft spot is that "follow-up" is never defined.

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?

Three short sentences, no filler, with the core capability front-loaded before the access and caching details. Minor cost: the compressed shorthand ("participation need", "follow-up") trades clarity for brevity.

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?

An output schema exists, so return values need not be described, and the safety annotations are handled. Still missing for a four-parameter discovery tool are the semantics of the focus enum values, any hint of pagination or result-window behavior beyond the cap, and any differentiation from the many sibling poll-listing tools.

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 0%, so the description must carry parameter meaning, and it only partly does. It maps implicitly to category ("topic"), focus ("participation need") and previous_snapshot ("snapshot_id" — note the name mismatch with the actual parameter), but the three focus enum values are never explained and "limit" is only obliquely implied by "up to five".

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?

"Find up to five open agent polls by topic and participation need" gives a specific verb (find), a bounded resource (open agent polls), and the two filtering axes (topic/category, participation need/focus). It is clear on its own, but it never distinguishes itself from siblings such as list_polls or get_poll, so an agent cannot tell from this text alone why it would pick one over the other.

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 provides useful invocation context: "Public, no enrollment" signals no auth prerequisite, and "Reuse snapshot_id to omit unchanged items" tells the agent when to resend a prior snapshot. However, it gives no when-not guidance and names no alternative tool, even though list_polls and get_poll are obvious candidates for overlap.

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