add_tuning_candidate

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

Annotations declare readOnlyHint=true and idempotentHint=true, but the description says 'Only its fingerprint and optional artifact reference are persisted,' indicating a durable write. This directly contradicts the read-only annotation.

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 deliver the core action and persistence behavior with minimal verbosity.

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?

The tool has six parameters and an output schema, but the description's brevity plus the contradiction leaves usage ambiguity. The persistence note is useful, yet the read-only annotation undermines trust in the description's completeness.

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?

The schema covers 67% of parameters with descriptions, including strategy enum and artifact_ref requirements. The tool description itself adds no parameter-level detail for database_name or idempotency_key; the fingerprint persistence note is tangential.

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 action ('Add one concrete rewrite or index experiment') targeting an existing tuning session, clearly distinct from session creation or benchmarking. The 'fingerprint' note emphasizes a lightweight candidate record.

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?

No explicit when-to-use or alternatives listed. Context implies use within an active tuning session, but there is no direct comparison to benchmarking or session tools.

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