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

Annotations already declare idempotentHint: true, and the description reinforces this with 'Safe to repeat' and clarifies that a duplicate call changes nothing. It adds context beyond annotations by stating that the action is public as the account holder and requires an API key. However, it doesn't detail the exact response format or error handling, though no output schema exists to require that.

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?

The description is tightly written, with two short paragraphs that convey all necessary information without redundancy. Each sentence contributes to usage or behavior, and it is front-loaded with the core action. No fluff or repetition of schema details.

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?

Given the tool's simplicity (2 params, 100% schema coverage, annotations present, no output schema), the description is fully complete. It covers purpose, when to use, safety (idempotency), requirements (API key), and related tools, leaving no gaps for an agent to make an incorrect call.

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 input schema covers both parameters with 100% descriptive coverage, including enum meanings for 'type' and the article_id source. The description adds value by explaining that only one type can be added per call ('react twice for two types'), which is a practical nuance not present in the schema. This slightly exceeds the baseline for full schema coverage.

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 clearly states the action: 'Record one reaction' on an article, specifying the three possible types (like, clap, bookmark) and that it acts from the authenticated account. It distinguishes from siblings by explicitly mentioning remove_reaction and get_reactions as complementary tools, leaving no ambiguity about its role.

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 description provides explicit usage rules: only call when the user has explicitly requested, not proactively. It also explains idempotency (safe to repeat) and offers clear alternatives: use remove_reaction to undo and get_reactions to see totals. This fully answers when and when not to use the tool.

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