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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is fully covered without the description. The description adds useful structural context (three-column status model, RSS-sourced items) but says nothing about ordering, the default page size, or what a result row looks like.

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, front-loaded with what the board is, then search, then the follow-on workflow. Minor ambiguity: 'post ideas in three columns' can momentarily read as the verb 'post' rather than 'ideas are posted here'.

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, the description must carry the burden of describing results; it conveys the board/column model and RSS inclusion but not pagination, ordering, or the shape of a returned idea. Adequate to call correctly, but thin for an untyped list response.

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?

At 67% schema coverage, q and limit are already documented in the schema, and the description's 'Search with q' adds nothing beyond it. The three column names do give meaning to the otherwise undescribed status enum, but that is a single contribution against a partially covered schema.

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 identifies the resource concretely: an ideas board with three columns (idea, drafting, ready) that also holds items imported from RSS feeds. That distinguishes it from get_idea (single item) and from list_feed_items (the raw feed), though it never uses an explicit verb like 'list' and never names those siblings outright.

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?

It gives usable context: 'Search with q' and a workflow chain ('use an idea as the starting point for create_post, then move it on with update_idea'), which tells the agent what this tool feeds into. It stops short of explicit when-not conditions or naming get_idea/list_feed_items as alternatives for single-item or raw-feed retrieval.

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