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

Annotations indicate readOnlyHint=false, destructiveHint=true, idempotentHint=false, but the description adds valuable nuance: some operations are unsigned plans, quote_proof creates a hosted job, pay_proof may transfer Base USDC after explicit approval, and authorize_relay may submit a proof after explicit approval. It also defines CompetitionSettledV2 as the only payment evidence. This goes beyond what annotations alone provide. Slight deduction because it doesn't explicitly mention destructiveness or persistence side effects beyond those operations, but for a multi-operation tool this is strong transparency.

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?

The description is compact given the complexity of the tool. Four sentences, each earning its place: the prerequisite, the schema-matching instruction, the operation-specific behavioral warning, and the evidence/next_action guidance. It front-loads the most critical usage rule (only after inspect guide) and keeps the rest tight. For a tool with ten conditional operations, this is well-structured and not bloated.

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 the tool is a dispatcher with many nested schemas and an output schema, the description does not need to restate return formats. It covers the key operational context: prerequisite, schema matching, approval-sensitive operations, payment evidence. The main gap is that it doesn't explain the relationship to all sibling tools (e.g., prepare_bounty_action) or describe how the output schema should be used beyond 'Follow next_action'. Still, for such a complex tool, this is nearly 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 100% across all operation-specific arguments, so the baseline is 3. The description adds important top-level semantic guidance: 'Follow next_action', 'treat only CompetitionSettledV2 as payment evidence', and 'Match arguments to the selected operation's exact schema'. These compensate for the enormous conditional schema and help the agent understand that 'arguments' is not a free-form object. However, the description itself doesn't enumerate parameter meanings because the schema already does; the added value is in cross-referencing the guide and next_action.

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 names a specific verb ('prepare') and resource (open competition V2 actions), and frames itself as a step to execute after inspect_open_competition_v2(operation=guide). It clearly indicates this prepares/executes operations within a competition lifecycle, distinguishing it from sibling tools like inspect_open_competition_v2 (inspection) and prepare_bounty_action (different bounty flow). However, the title 'Prepare V2 action' is vague without the description, and the description could better contrast with prepare_bounty_action for the open-competition versus general-bounty distinction. Overall, the purpose is clear.

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?

Explicitly says 'Use this only after inspect_open_competition_v2(operation=guide)', giving a precise prerequisite and pointing to the guide that selects the operation. It also instructs to 'Match arguments to the selected operation's exact schema', and warns about operations that return unsigned plans and require explicit approval. This is strong when-to-use guidance with an explicit alternative/previous-step reference.

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