begin_transaction

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

Discloses key behavioral traits: starts a transaction, affects subsequent writes, single active constraint, failure if already in transaction. Although no annotations exist, the description fully compensates with clear statements about behavior and return values.

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?

Highly concise: two paragraphs covering purpose, mechanism, return structure, and notes. No unnecessary words, well-organized for quick parsing.

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 zero parameters and an implied output schema (described inline), the description is fully complete. It covers what the tool does, when to use it, its constraints, and what it returns, leaving no gaps for correct invocation.

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?

No parameters exist in the schema, so the description's role is primarily to explain behavior and output. It adds meaning by detailing the return dictionary structure and transaction lifecycle, which goes beyond the empty schema. Baseline for 0 parameters is 4.

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 tool begins a database transaction and explains its role in the context of subsequent write operations. It distinguishes itself from sibling tools like commit_transaction and rollback_transaction by explicitly naming them as complementary actions.

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 explicit guidance: use before write operations, explains lifecycle with commit/rollback, and warns that only one transaction can be active at a time. No alternative usage scenarios need clarification.

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