data_sqlite_query

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

With no annotations, the description carries the full disclosure burden and does well on the most important trait: it is explicitly read-only and states that writes and DDL are blocked. It says nothing about permissions, query timeouts, error behavior, or how results are returned, so the disclosure is partial.

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 short sentences with the read-only constraint front-loaded. Nothing is wasted and the critical restriction appears before the caveat.

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?

An output schema exists, so return values need not be explained, and the safety profile is covered. However, for a tool that takes an arbitrary filesystem path and an arbitrary SQL string, the absence of any path-resolution or limit guidance leaves real gaps for an agent composing a call.

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% for three parameters, so the description must compensate and largely does not. 'SELECT/WITH' and 'SQLite file' give indirect meaning to sql and path, but path resolution (sandbox-relative? absolute?) and the purpose of limit (default 100) are entirely undocumented.

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?

States a specific verb ('Run') and resource ('SQL query against a SQLite file in the sandbox') and constrains it to SELECT/WITH. The SQLite-file resource implicitly separates it from data_read_csv and data_read_json, though no sibling is named explicitly.

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 usage through the SELECT/WITH constraint and the note that writes and DDL are blocked, giving the agent a clear picture of the allowed operation class. It never says when to prefer this over data_read_csv or data_read_json, nor what to do when a query is rejected.

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