Submit CASDA async TAP query

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

Annotations give readOnlyHint=false and destructiveHint=false, but the description adds that 'Create and RUN are never automatically retried', which is not covered by annotations. It also implies the tool expects pre-validated ADQL, adding behavioral context beyond 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?

Two sentences: first states the function, second gives requirements and retry behavior. No wasted words, front-loaded with the core purpose. Excellent conciseness.

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?

Given a single parameter and existence of output schema, the description covers the main purpose, a precondition, and retry policy. It omits error handling or chaining with result retrieval tools, but for a submission tool, it is largely 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?

With 100% schema description coverage, the schema already describes the query parameter as 'SELECT-only ADQL submitted as an async TAP/UWS job.' The tool description adds 'validated' and the precondition, but these are marginal additions. Baseline 3 is appropriate as the description adds limited value 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 clearly states 'Create and start one async TAP job for validated SELECT-only ADQL', specifying the verb (create, start), resource (async TAP job), and constraint (SELECT-only ADQL). This differentiates it from siblings like casda_tap_query (likely sync) and casda_validate_adql (only validation).

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 mentions a precondition ('Requires CASDA_ENABLE_ADVANCED_ADQL') and a behavioral note ('Create and RUN are never automatically retried'), providing context for when to use the tool. It does not explicitly compare to alternatives, but the async nature and SELECT-only restriction imply usage situations.

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