read_election_windows

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral value by stating that each returned window bundles chart, direction candidates, and judgment rules, but it omits pagination behavior (that only up to 14 windows come back at a time) and any cost or size characteristics.

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?

A single compact sentence that front-loads the verb and resource and appends the payload contents. Nothing is wasted, though the description is short enough that its omitted pagination detail is a sizing trade-off rather than pure conciseness.

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 0% parameter coverage, the description must carry the load, yet it omits pagination semantics, the 14-item cap, and what artifact_id refers to. Given the sibling set of build/render/preview calendar tools, an agent lacks the detail needed to invoke this 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?

Schema description coverage is 0%, so all three parameters (artifact_id, limit, offset) are undocumented in both schema and description. The description never explains that artifact_id selects the generated material or that limit is capped at 14 and offset drives paging, leaving the agent to infer parameter meaning entirely.

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 pairs a concrete verb ('读取' / read) with a specific resource ('小批次窗口' / small-batch windows) and then enumerates what each window contains: complete chart, direction candidates, and judgment rules. That content list goes beyond the name and helps an agent recognize the payload, though it never distinguishes this tool from the render/preview calendar siblings.

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?

'已生成材料中的' (within already-generated materials) implicitly tells the agent this only reads from an artifact that must already exist, which lightly contrasts with the build_* siblings. However, it gives no explicit when-to-use, no exclusions, and no routing versus render_election_calendar or preview_election_calendar.

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