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

Goes well beyond the destructive/openWorld annotations: it discloses the refund of unspent budget, the fully-paid-out failure mode, that it only prepares an unsigned intent (nothing executes until signed), and the irreversible two-step confirm_token flow. This is rich behavioral context an agent needs.

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-loads the action and its consequence, then layers the failure condition, the intent/signing workflow, and the irreversibility note. Dense but every sentence carries information the caller needs.

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?

For a destructive on-chain mutation with no output schema, it covers what is destroyed/refunded, the required signing workflow, and the confirm_token return value. Nothing an agent needs to invoke it correctly is missing.

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 75% and the schema only says `length` is an integer 0-255; the description supplies the critical constraint that it must be 1, 3, or 5, which is essential to call correctly. It also explains confirm_token's role in the two-step flow.

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?

Specific verb+resource ('Close one of your surveys') with scope and consequence spelled out (unspent budget refunded). It clearly distinguishes itself from sibling read tools like geode_surveys_get_my_surveys by describing the closing/refund behavior.

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?

Gives a clear precondition ('Fails if the budget is already fully paid out') and names the follow-on workflow tools (geode-local-signer, geode_submit_intent). It doesn't, however, state explicit alternatives or when-not-to-close beyond the single failure condition.

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