akb_sql

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

With no annotations present, the description carries the full safety and behavior burden, and it does a solid job: it discloses that tables are real PostgreSQL tables, that SELECT needs a reader role while writes need a writer role, and that results are never silently truncated so unbounded SELECTs can return very large payloads. It does not fully specify behavior around DDL support, transaction/commit semantics, or the exact result shape, which prevents a perfect score.

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 front-loaded with the core purpose, then proceeds logically through naming, cross-vault usage, roles, and the LIMIT warning. Every sentence earns its place, and no information is redundant with the schema. Despite covering multiple important caveats, it is compact and easy to parse.

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?

Considering the moderate complexity of a SQL execution tool with auth, cross-vault, and large-result concerns, the description covers the most operationally critical details well. The main gaps are that it never states whether DDL statements are supported (and if not, which sibling tool to use) and it does not describe the structure of the returned result set, which matters more because there is no output schema.

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 input schema already documents all four parameters, so the baseline is 3, but the description adds meaningful semantics on top: it explains that table names are auto-resolved to vault tables and introduces the sales__pipeline-style prefix convention for the vaults/vault parameters. It also reinforces the LIMIT guidance already present in the sql parameter description. The _vault_skill_ack parameter is not further elaborated beyond the schema, but it is already clearly described there.

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 opens with a clear verb and resource: 'Execute SQL on vault tables.' It further specifies that these are real PostgreSQL tables and explains table-name resolution, which distinguishes this tool from sibling table-management tools like akb_create_table and akb_drop_table. An agent can immediately tell this is for running queries/DML against vault data rather than for more general data access.

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 strong practical context: when to use the vaults parameter, how to prefix table names for cross-vault queries, role requirements for SELECT vs. INSERT/UPDATE/DELETE, and a clear LIMIT instruction to avoid oversized responses. However, it does not explicitly name sibling alternatives or state when not to use this tool (e.g., for DDL or object-level access), so it stops short of full when/when-not guidance.

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