run_sql

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses read-only behavior ('No writes, no ATTACH'), PII column blocking ('raw_ofx, payee, memo, acct_hash are read-blocked'), and the visibility of all statuses. This provides comprehensive behavioral transparency.

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 three concise sentences, each adding valuable information. It front-loads the primary action and resource, then efficiently covers status filtering and restrictions. No unnecessary wording or repetition.

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 simple schema (1 parameter), no annotations, and no output schema, the description is remarkably complete. It defines inputs, acceptable queries, unavailable columns, and the status nuance. The column list effectively serves as the output schema, enabling the agent to understand return values without additional documentation.

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 schema provides no description for the 'query' parameter, but the description compensates by explaining the query type ('SELECT/WITH'), constraints ('No writes, no ATTACH', PII blocked), and the available columns. This adds meaningful semantic context, though it stops short of giving explicit syntax examples or stating 'provide a SQLite query string'.

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's function: 'Run a read-only SELECT/WITH query against the transactions table', specifying the exact resource and verb. It also lists the accessible columns, distinguishing it from higher-level sibling tools by emphasizing its SQL nature and read-only scope.

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 context about read-only usage and notes 'add WHERE status='posted' to match the spend tools'. However, it does not explicitly name alternatives or state when to prefer this tool over siblings like query_transactions. The usage guidance is implied rather than explicit.

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