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

The description explicitly states `burn` 'destroys exactly the pool's stake ... a real token burn, supply falls', which is a destructive update to the environment, while the annotations declare destructiveHint=false. This directly contradicts the annotation. (The extra context about irreversibility, parking of unknown-result burns, and JWT auth is otherwise valuable, but the conflict governs the score.)

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?

Dense but efficient: the outcome semantics, refusal codes and preconditions are front-loaded, and each clause carries information. The single long sentence is harder to scan than it needs to be, but there is little waste.

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 mutation tool with no output schema, it covers error codes, irreversibility, the once-per-pledge rule, parking behavior and auth. It does not describe the response body an agent receives, which is the main remaining gap.

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 100%, so baseline is 3, but the description adds real meaning beyond the schema: it explains the 1-16 batch bound, defines `burn` vs `release` semantics, and notes the pledge must come from the organiser's own locked pool. The `burn`/`release` enum values carry no description in the schema, so this compensates well.

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 ('give ... outcomes' to funded pledges in your locked pool) and clarifies the scope of the pool. It differentiates by workflow (result must be published first) but never names the sibling tool that publishes the result, so the distinction rests on inference.

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 and sequencing rule: publish the result first, otherwise `result_required`/`outcome_not_in_result` is returned. It also bounds the batch to 1-16. It does not name alternative sibling tools (e.g. pool_result, pool_cancel) or say when not to call this.

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