sql_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 so well: read-only, recent-rows-only scope, `body` column semantics, and timeout risk on ORDER BY. It also flags the need to prefer `recent_events` for retrieving lines, which is a behavioral boundary.

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?

Three sentences, each carrying load: purpose, schema hint, and constraints/alternative. The key constraint (no ORDER BY) is stated immediately before the alternative, making it 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?

For a one-parameter read-only query tool with no output schema, the description is complete enough: it names the table, relevant column, recency scope, and a timeout hazard, and routes to the correct sibling. No critical calling information is 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 0%, but the description compensates by explaining that the `sql` parameter must be a SELECT on `occurrences`, must be filtered, and must avoid ORDER BY. It could be improved with a concrete example or accepted SQL patterns, but the core semantics are conveyed.

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 states 'One read-only SELECT for a specific filtered lookup' and identifies the target resource (`occurrences`) with its relevant `body` column. This distinguishes the tool from siblings such as `recent_events`, which is recommended for retrieving actual log lines.

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?

It tells the agent when to use the tool (a single filtered read-only lookup) and explicitly says when not to use it: no ORDER BY over occurrences because it times out. It also points to `recent_events` as the preferred alternative for actual lines.

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