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

Goes well past the annotations: it explicitly states the tool reads only call-supplied material with no network request, fetch, wallet lookup, order, payment or external write, corroborating openWorldHint=false and readOnlyHint=true. It also discloses cost (0.10 USDC per call on Base via x402 exact), the 10 free signed-wallet calls per rolling 30 days, the X-Wever-Wallet-Proof binding requirement to the exact JSON arguments and route, and the Ed25519 signed receipt in the return value — all behavior an agent cannot infer from structured fields.

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?

Almost every clause carries real information, but the opening sentence is a long run-on that buries the core verb and mixes inputs, outputs and verdict into one breath. Later fragments ("Paid URL: 0.10 USDC per call...", "Contract: /api/job-records-contract") are terse but readable; overall the structure is a dense wall rather than front-loaded guidance.

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?

With no output schema, the description does the heavy lifting on return values (signed brief with itemized costs, failed runs on their own line, margin, cost per output, verdict) and covers payment and proof-binding mechanics. It stops short of describing error/failure behavior or what happens when amounts are mixed-asset, which for a paid, 10-parameter tool leaves a small 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 description coverage is 100%, so the schema already documents every parameter including nested record shapes. The description restates the record contents ("each with amount, asset and label") and flags output_count as optional, but adds little semantic detail the schema lacks — notably it never surfaces the anyOf constraint that at least one of payments_received/payments_made/compute_spend/failed_runs must be present.

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 and resource (submit one job's records, plus deliverable and output count) and states precisely what artifact comes back: gross in, itemized costs, net and margin, cost per finished output, and a loss/break_even/profitable verdict. It distinguishes itself from the two nearest siblings by naming them (wever_expense-close-pack for monthly, wever_wallet-statement for live wallet activity), so an agent can route without opening a 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?

It gives explicit alternative routing: per-job economics go here, monthly close packs go to wever_expense-close-pack, live wallet activity to wever_wallet-statement. It also signals the optional input ("where you have it, the count of finished outputs"). What's missing is any negative guidance about when this tool is not appropriate (e.g., cross-job or multi-job rollups), which keeps it short of a 5.

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