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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses two real behavioral traits: a 10,000-row cap on the result and a publicly accessible download link with a sharing warning. That security/data-exposure note is exactly the kind of context annotations cannot convey. It stops short of 5 because permission requirements and query-timeout/error behavior are unstated.

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, zero filler, with the core action, the row limit, the return value, and the sharing caveat all front-loaded. Every clause earns its place.

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?

With no output schema, the description correctly states the return (a download link) and adds the row cap and public-link caveat. For a two-parameter export tool this is nearly complete; only auth/permission context and behavior on invalid or oversized SQL are missing.

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 50%: only 'filename' is documented ('Without extension') while 'sql' is bare. The description partially compensates by stating the sql argument must be a single SELECT capped at 10000 rows, but says nothing about the filename parameter or naming rules. Adequate, not additive beyond the schema.

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 gives a specific verb+resource+output: 'Run one SELECT and save the result as a CSV file (up to 10000 rows); returns a download link.' That is far more informative than a restated name. It never differentiates itself from query-running siblings like run_sql or dispatch_query, so it stops short of a 5.

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?

Usage is only implied: an agent can infer this is the tool to reach for when a CSV deliverable is wanted, and the 'one SELECT' phrasing hints at a single-statement constraint. There is no explicit when-to-use vs. run_sql/dispatch_query guidance or any stated prerequisite (e.g., workspace scope or permissions).

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