Commission a capture (post a bounty)

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

With no annotations, the description carries the full burden and does so well: it discloses immediate USDC payment on Base or Arc mainnet, refund-on-cancel/deadline behavior, server-quoted amount limits (default 50–5000), and that the bounty token is stored locally so later tools only need bounty_id. This is exactly the behavioral context an agent needs before committing funds.

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?

Front-loaded with the core action and payment consequence, then the workflow, then constraints. It is dense and runs as one long paragraph, but nearly every clause earns its place; a break into workflow vs. constraints would slightly improve scanability.

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?

There is no output schema, and the description implies the return contains a bounty_id but does not state the response shape explicitly. Otherwise it fully covers the action, cost, refund path, and follow-up tools, making it complete enough for correct invocation.

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 coverage is already 100%, so the schema documents field constraints. The description still adds value the schema lacks: the server-quoted amount band (50–5000, overriding the schema's misleading minimum of 1) and the deadline default of 7 days, which the schema does not state. That is meaningful supplementation 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?

States a specific verb+resource ('Commission a ground-level 3D capture of a real place') and immediately frames the mechanism as posting to a bounty board, which cleanly distinguishes it from siblings like vangrid_coverage_query and vangrid_verify_provenance. An agent can identify this as the create-a-bounty entry point without opening the schema.

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 routes the agent through the lifecycle and names the sibling tools for each step: review with vangrid_bounty_status, accept with vangrid_accept_submission, and the implicit cancel path via vangrid_cancel_bounty. It also states the triggering condition for refunds (no acceptance by deadline, or cancellation while open).

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