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 real work: it declares the operation read-only, enforces a single statement per call, bans write keywords, and caps returned rows. It stops short of saying what happens on violation (error vs. truncation), whether there are timeouts, or what permissions the caller needs.

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: capability and read-only scope first, then the schema pointer, then a compact limits line. Every clause adds usable information and nothing is padded.

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?

For a free-form SQL tool with no annotations and no output schema, the definition covers the essentials an agent needs: safety profile, statement limit, row cap, and where to find schema. It omits error semantics and whether results are truncated or fail when exceeding `max_rows`.

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 0%, so the description must compensate, and it largely does: `query` is constrained to a single SELECT with no write keywords, and `max_rows` is explained as the row-count ceiling. It does not give SQL dialect, syntax examples, or default-behavior detail beyond the schema's `default: 200`.

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 and resource: 'Executa um SELECT livre no banco (somente leitura)'. The word 'livre' (free-form) implicitly contrasts with the twelve prebuilt analytics siblings, but no sibling is named, so differentiation is inferred rather than explicit.

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?

Gives concrete usage context: read the schema at `isp://schema` first, one statement per call, no write keywords, capped at `max_rows`. It never says explicitly when to prefer this over siblings like `churn_by_month` or `ticket_stats`, so the routing decision is left partly to inference.

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