get_poll_results

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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds specific behavioral context: 'reads local cache; works while disconnected', which suggests it is suitable for offline scenarios and may return stale data. It also notes that zero-vote options are included, which is helpful. There is no contradiction with annotations.

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 extremely concise: two sentences, with the most critical usage context ('reads local cache; works while disconnected') placed first. Every word contributes value, and there is no unnecessary elaboration.

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 the tool's simplicity (two required parameters, no output schema), the description covers the main purpose and key behaviors. However, it does not explain what format the 'current tally' is returned in, nor does it clarify what happens if the poll is not cached. This leaves minor gaps that could affect an agent's ability to use the output correctly.

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?

Both parameters are fully described in the input schema (100% coverage), so the description's job is minimal. It does not add any additional meaning beyond the schema, meeting the baseline expectation without exceeding it.

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 clearly states the action ('Return') and the resource ('current tally for a cached poll'), and distinguishes the tool as a read-only counterpart to poll creation/voting. However, it does not explicitly differentiate it from any other poll-related read operation because no such sibling exists, so it loses a point for not preempting potential confusion with a non-existent sibling.

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 includes a useful use context: 'reads local cache; works while disconnected', which guides when to use this tool. However, it provides no guidance on when not to use it (e.g., if fresh data is needed) and does not name any alternative tools, leaving the agent to infer that this is the only poll results tool. This is adequate but not exemplary.

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