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

Annotations already declare readOnly/openWorld/non-destructive, but the description goes well beyond them: 24-hour caching, a 20-per-day per-person quota surfaced in the response, the 50-post cap and what summary.capped means, and a caveat that seedCandidates are candidates rather than proven keywords. That is substantive behavioral context an agent cannot get from structured fields.

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?

Front-loaded with the core purpose and tightly packed with useful facts, but several sentences are long and clause-heavy, so a reader has to parse a lot to extract the quota and cap details. Little is wasted, though it could be broken into cleaner units.

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?

There is no output schema, so the description correctly carries the return-value burden, naming the fields it produces (seedCandidates, summary.oldest/newest/capped, flags, thresholds.lowIntentPct). Combined with cached/quota/403 details, an agent has everything needed to call and interpret this tool.

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 100%, so the schema already documents both 'blog' and 'workspaceId' in detail (including the do-not-ask-again guidance). The description adds no additional parameter meaning, so the baseline 3 applies.

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?

States a specific verb and resource ('Reads a blog's public RSS feed... says whether the titles are written for search') and scopes it to Naver Blog only. It enumerates the concrete outputs (intent share, date/episode prefixes, posts per month, categories, repeated words), which distinguishes it from keyword-research siblings like research_naver_keywords and expand_naver_keywords.

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?

Explicit when-it-works context: any public blog, not only connected ones, no Naver keys required. It also gives operational conditions — cached 24 hours, a cache miss costs one of 20 daily diagnoses — and the exact failure path (403 research_tool_disabled with enableUrl, plus the instruction to tell the person once and not retry).

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