legion_sponsor

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

With no annotations at all, the description carries the full burden and does so well: it discloses that real sBTC is spent irreversibly with no refund path, that funds are metered against the wallet's sats spending limit before signing, and that an unlocked wallet is required. It also warns that name/link/memo are unverified and that the paying principal plus txid are the real identity.

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 core distinction is front-loaded in the first sentence, followed by economic consequences and then the safety warning, which is the right order. The closing 'Tip: call earning_opportunities...' is promotional filler that does not help an agent invoke this tool and slightly dilutes focus.

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 4-parameter mutation with no annotations and no output schema, this is nearly complete: cost source, irreversibility, auth prerequisite, pre-signing limit check and the trust status of the free-text fields are all covered. The gaps are the unnamed alternative (legion_contribute) and no mention of what failure looks like when the treasury minimum is not met.

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 3 is the baseline, but the description adds real meaning beyond the schema: name, link and memo are explicitly unverified metadata, while the principal and txid form the actual on-chain identity. It also explains why sats does not raise the join price but does enlarge payouts.

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 and resource (fund the pool) and immediately qualifies the variant ('WITHOUT minting voting weight, with a name on the record'). That negation effectively separates it from legion_contribute, but the sibling is never named, so an agent must infer the pairing from the naming pattern.

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?

The 'WITHOUT minting voting weight' clause implies when this is the right choice over a weight-minting contribution, and the tip routes to earning_opportunities for a different purpose. However, there is no explicit 'use legion_contribute instead if you want voting weight' statement or statement of when-not to sponsor.

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