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

Goes well past the annotations (destructiveHint=true, readOnlyHint=false): it names protected tables (review_events, hidden FSRS state), batch limits (50 statements, 100 affected rows each), array literal syntax, and RETURNING semantics. This is the kind of constraint detail an agent cannot infer from structured fields.

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?

Front-loaded with the core write/dialect constraint, then dense constraint clauses; every sentence carries information, though the run of dialect rules makes it longer than strictly needed.

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 an output schema covering return values and annotations covering the safety profile, the description supplies the remaining operational constraints (limits, protected resources, dialect quirks) an agent needs to call this correctly.

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 100%, so the schema already documents both parameters; the description adds dialect-level meaning for the sql value (allowed statement types, batch and row caps, OVERLAP tag filtering, UNNEST restriction) that the terse schema description omits.

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 (writes) and resource (workspace cards/decks via INSERT/UPDATE/DELETE) and explicitly excludes the sibling read path by noting it 'rejects read statements', separating it from sql_query.

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?

Clearly signals the write context and rules out read statements, which routes the agent to sql_query, but it never names the alternative tool or states prerequisites for selecting this one.

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