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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds meaningful context beyond those flags: the returned content is illustrative draft templates rather than live poll data, which prevents an agent from treating the output as real polls or voting results.

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 short sentences with the positive scope front-loaded and the exclusion clause second; nothing is padding. The 'for agents' phrase is slightly vague but harmless.

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-value description is unnecessary, and annotations cover safety. The description supplies the one behavioral fact an agent needs (the content is illustrative templates). The only meaningful gap is explicit routing against get_poll_format and list_polls.

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?

The tool takes no parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter detail is required.

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 uses a specific verb and resource ('Read illustrative draft question templates') and immediately clarifies what the tool does not return (live polls, simulated votes, publication), which separates it from get_poll and list_polls. It stops short of naming those siblings explicitly, so it is clear but not maximally distinguishable.

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 negative clause 'No live polls, simulated votes or publication' implies this is not the tool to call for actual poll data, which nudges an agent toward get_poll or list_polls. However, it never states when to use this tool, no prerequisites, and no alternatives are named.

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