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

Annotations already declare read-only, non-destructive, non-open-world behavior, and the description adds substantial context beyond them: newest-first ordering, the meaning of an empty list, and a concrete failure mode (403 with enableUrl) plus retry policy. It surfaces an operational constraint the agent could not derive from the schema.

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?

Four front-loaded sentences with no filler: payload, interpretation, empty case, then error handling. Each sentence carries distinct, actionable information and nothing is repeated from the schema.

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 carries the return-shape burden and does so fully (per-day points, ordering, three metrics), plus edge cases and error handling. An agent has everything needed to call it correctly and react to failures.

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 coverage is 100%, so the schema already documents all three parameters including defaults and the workspaceId conditional. The description adds no parameter-level syntax or format detail beyond what the schema states, so the baseline of 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?

The description names a specific verb and resource ('the measurement history of one keyword') and specifies the grain, ordering, and payload ('one point per day it was actually measured, newest first, with search volume, document count and posts per month'). This cleanly separates it from research_naver_keywords, expand_naver_keywords and list_naver_keyword_reports.

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 explicit runtime guidance for the disabled-tool case (403 research_tool_disabled with enableUrl, tell them once, do not call again until re-enabled) and explains the empty-list meaning. What it lacks is a direct statement of when to prefer this over the sibling research_naver_keywords call, though the 'history' framing implies it.

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