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

Adds context beyond annotations: clarifies scope (leaves other reactions, doesn't delete article/comments), idempotency ('removing a reaction that is not there succeeds and changes nothing'), and requirement for API key. No contradiction with annotations (readOnlyHint false, destructiveHint true, idempotentHint true).

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 well-structured paragraphs: first states purpose, second details scope, third covers safety, auth, and recommendation. Each sentence is purposeful, no redundancy, and information is front-loaded.

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?

For a simple 2-parameter tool with annotations, the description covers purpose, scope, behavior, auth, and usage guidance. It does not mention return values, but no output schema exists and it's a removal action; this is acceptable given the context.

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% with good descriptions. Description adds value by explaining that 'type' only removes that specific reaction without affecting others, and for article_id points to the 'id' field from article tools. This enriches the schema beyond the basic definitions.

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?

Clearly states 'Withdraw one reaction the authenticated account previously left on an article' with a specific verb and resource. It explicitly distinguishes from siblings by noting it removes exactly the type named and leaves other reactions intact, contrasting with add_reaction.

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?

Provides usage context by recommending 'Call get_reactions first if you need to know what is currently set.' It implicitly distinguishes from add_reaction and emphasizes idempotent behavior ('Safe to repeat'). Does not explicitly mention when not to use it, but gives clear practical guidance.

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