run_gaql

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description reinforces this by stating 'read-only,' 'cannot write,' and 'Only SELECT is accepted,' adding GAQL-specific nuance beyond the annotations. It also discloses that the tool returns raw rows, which is useful behavioral context.

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 no filler. The core action, output, and constraining rule are all front-loaded, and every sentence adds unique value.

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 an arbitrary query escape hatch, the description covers the essential behavior, the read-only guarantee, and the SELECT-only restriction. An output schema exists, so the return shape does not need description. The only notable gap is parameter documentation, but the tool's simplicity and escape-hatch framing keep it adequately complete.

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%, so the description carries the burden for parameter meaning. It implicitly defines the 'query' parameter as a GAQL query, but it does not explain 'customer_id' or 'limit' at all. The description provides minimal help for the two required parameters and one optional parameter.

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 uses a specific verb-resource pair ('Run an arbitrary read-only GAQL query') and clearly states the output ('return the raw rows'). It also distinguishes the tool from siblings by calling it an 'escape hatch for anything the other tools do not cover,' making its role unmistakable.

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 explicitly frames this tool as a fallback for anything other tools do not cover, which is clear usage context. It also gives a hard constraint ('Only SELECT is accepted'). It stops short of naming specific alternative tools or saying when NOT to use it, so it is clear but not fully exhaustive.

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