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

Annotations already declare readOnly, idempotent, non-destructive, open-world, but the description adds non-obvious traits: it is free, keyless, stores nothing about the person, and therefore cannot know the last-check time unless `since` is passed. That is exactly the kind of context annotations cannot carry. It omits anything about result size or pagination, keeping it from a 5.

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 inventory is front-loaded in the first sentence, which is good, but the prose is dense and oversized, and the free/keyless claim is stated twice ('Free, keyless, read-only…' and again 'Cost and signer: free and keyless, nothing to sign'). Several clauses could be trimmed without losing information.

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?

An output schema exists, so return shape need not be spelled out; the description still enumerates what categories of results come back and why. Privacy, cost, and auth posture are covered, leaving only minor gaps such as expected result size. Complete enough for an agent to call it correctly.

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 the baseline is 3, but the description adds rationale the schema lacks: it explains why `since` matters (nothing is stored, so without it everything is listed) and ties the nearby-work section to the optional location input. It does not restate wallet/near mechanics beyond that, which is appropriate.

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?

Uses a specific verb-plus-resource framing: it returns everything for ONE wallet — claimed packets, their statuses, pending/rejected proofs, settled receipts, and nearby open work. An agent can tell it is a personal dashboard rather than a search or single-packet lookup, though it never names the nearest siblings (work_status, my_ledger, my_next_step) to sharpen the distinction.

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 concrete trigger questions — 'how their work is going, whether they got paid, whether anyone reviewed their proof, or what to pick up next' — which maps cleanly onto user intents. It also explains the operational context (no email or notifications, so this is how a person stays with the process). No explicit when-not-use or named alternatives, so it stops 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.