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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds a cost indicator ('1 credit') and implicitly mentions the fresh parameter's extra cost via schema. This goes beyond annotations by disclosing pricing. It does not contradict any annotation and adds useful behavioral context about cost, which is not present in 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?

The description is two short sentences with zero waste. It front-loads the core function ('One tweet by numeric id') and appends the cost note. Every word earns its place, and the structure is easily scannable for an agent.

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 single-tweet fetch, the description covers the essential: what it returns (tweet with author) and cost. It does not mention return format, but that's not required given no output schema and the tool's simplicity. The annotations handle safety. The description is complete enough for an agent to invoke correctly without missing critical information.

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 50% (only 'fresh' has a description). The description adds 'numeric id' to clarify the 'id' parameter, which is partially compensating. However, it doesn't explain the 'fresh' parameter, though the schema already does. The description provides some meaning for id beyond the schema pattern, but not for all parameters. Overall, it adds marginal value but does not fully cover the gap.

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 operation: fetch a single tweet by numeric id, and notes it includes the author. This distinguishes it from sibling get_tweets (plural) and get_user_tweets (user-scoped). The verb is implied from the tool name but the resource and scope are specific. It could be more explicit about alternatives, but the singular 'tweet' vs plural siblings provides differentiation.

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 gives no explicit guidance on when to use this tool versus the many siblings. It implies usage for a single tweet by id, but does not mention alternatives or exclusion criteria. For example, it doesn't state 'use get_tweets for multiple tweets' or 'use search_tweets for queries.' The context is partially clear from the name, but the description itself lacks explicit usage direction.

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