plan_sub_query

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

No annotations exist, so description carries full burden. It discloses batch submission, validation rules (unique ids, no cycles), error on duplicate, and is_revision effect. However, missing details on result behavior (e.g., return value, idempotency).

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?

Description is well-structured with bullet points and a JSON example. Front-loaded with purpose. Could be slightly more concise by omitting standard validation details, but overall efficient.

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?

No output schema exists; description does not explain return values or error responses. Prerequisites are implied by required session_id from plan_intent. Missing post-submission context (e.g., success indication, session state changes).

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 already covers 100% of parameters. Description adds significant value for items_json by specifying exact JSON shape, validation constraints, and the purpose of is_revision. Other parameters (session_id, thought, confidence) are not enhanced beyond schema, but the critical parameter is well-explained.

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?

Clearly states the tool submits ALL sub-queries in one call (batch). Verb 'submit' and resource 'ALL sub-queries in ONE call' are specific. Mention of 'Phase 3' distinguishes it from earlier planning phases.

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?

Only implies phase context ('Phase 3'), but no explicit when-to-use or when-not-to-use. No comparison to sibling tools like plan_intent or plan_execution. No guidance on choosing is_revision vs not.

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