query

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

With no annotations, the description carries the full burden and explicitly discloses 'read-only', which is a key safety trait. It also scopes queries to 'canonical entities', setting expectations about the data model. However, it omits potential side effects, permission requirements, or query constraints beyond the schema defaults.

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 a single, clear sentence that front-loads the action and purpose. It avoids unnecessary detail and is highly 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?

The description covers the core purpose and read-only nature, but lacks usage alternatives, parameter details, and differentiation from sibling check_query. With no output schema or annotations, it leaves the agent to infer important context like what 'canonical entities' are and whether any query limitations apply.

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 0% and the description provides no additional meaning for the 'sql' or 'max_rows' parameters. While the parameter names are self-explanatory, the description does not clarify the SQL dialect, the nature of canonical entities, or how max_rows behaves, leaving a significant 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 tool runs a read-only SELECT/WITH query over canonical entities and returns rows. The verb 'Run' paired with a specific query type and target resource thoroughly distinguishes it from report-oriented siblings like weekly_report and describe_model.

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 implies use for ad-hoc data retrieval with read-only SQL, but it does not explicitly state when to use this tool over alternatives like check_query, nor does it provide exclusions. The role of 'canonical entities' is left undefined, weakening contextual guidance.

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