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

Beyond annotations (readOnlyHint=true, destructiveHint=false), the description adds the 500-row cap, pagination via offset, and the has_more continuation flag—crucial runtime behaviors an agent must know. It also clarifies that 'where' uses exact matching. These disclosures exceed annotations and help prevent failed or oversized calls.

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?

Two sentences deliver purpose, filter semantics, row cap, and pagination instruction with zero fluff. The example for 'where' is compact but illustrative. Information is front-loaded with the action first, followed by key constraint.

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 tool's complexity (8 parameters, nested objects) and existing output schema, the description covers the primary usage, pagination boundary, and filter behavior. It does not explicitly mention ordering expectations or response shape, but those are documented in the schema/output schema. The description is sufficient for correct invocation in most cases.

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 high (88%), but the description adds meaning for two sparse parameters: 'offset' (pagination) and 'where' (exact matches, with an example). The 500-row limit also gives context for 'limit' and 'offset'. This pushes beyond the schema's 'Column equalities' and the bare offset field.

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 a specific action ('Read rows') on a specific resource ('one table of the app's database'). This distinguishes it from sibling tools like insert_database_rows, delete_database_rows, and update_database_rows, and the 'one table' qualifier helps separate it from run_database_sql.

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 the intended usage (reading rows with equality filters) and provides operational details like pagination and max rows, but it does not explicitly contrast with alternatives (e.g., when to use run_database_sql for complex queries or why not to use this for updates). Usage context is present but not explicit.

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