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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, and the description is consistent with that ('Reads only the material in the call: no network request, fetch, money movement, message, sharing, configuration change or external write'), so no contradiction. Beyond the annotations it adds materially new behaviour: 0.10 USDC per call on Base via x402 exact, 10 signed-wallet free calls per rolling 30 days, the requirement to bind X-Wever-Wallet-Proof to the exact JSON arguments and route, the Ed25519-signed report/receipt output, and the specific defect taxonomy plus fixes the report returns. That is exactly the kind of cost, auth and output context annotations cannot convey.

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 information is dense and each block is directionally front-loaded (input description, then report/verdict, then siblings, then endpoint, safety, pricing, auth, return). But it is delivered as a single sprawling run-on enumeration that repeats verbatim the schema's enum lists (JSON, CSV, verifiable credential, on-chain, PDF, HTML, proprietary, none) and becomes hard to parse. Tightening the parameter walkthrough and keeping the distinctive material (verdicts, defect list, pricing, header binding) would raise this to a 5.

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?

There is no output schema, yet the description supplies the return semantics: a signed Ed25519 report naming a primary defect plus the full set of defects and fixes (platform-locked record, missing export format, non-verifiable outside the issuer, unreadable export, partial export, on-request-only export, unpublished key, loss on closure, rewritable entries, no other accepting platform) and the four verdicts. Combined with endpoint, contract link, human page, pricing and auth requirements, an agent has everything needed to call it and interpret the result.

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 only 33% across six parameters with nested objects, so the description has to carry weight, and it does: it enumerates the held_by options (issuer account, agent, both, third party), the bound_to targets (platform account, agent key, DID, wallet, domain, other), the export format and payload contents, the verification method options plus 'works with no account at the issuer' and 'key is published', closure survival and issuer rewrite, and accepted_by as 'platforms beyond the issuer'. This effectively re-documents the low-coverage nested schema in prose and adds interpretation, though it largely restates the enum values already 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 states a concrete operation on a concrete resource: submit a description of how one reputation record is stored (platform, holder, binding, export, verification, closure, acceptance) and receive a signed report assessing portability. It also names the three closest siblings (wever_identity-portability-check, wever_memory-export-check, wever_receipt-passport) and the verdict set, so an agent can separate it from neighbours. It loses a point because it opens with an indirect 'submit how…' framing rather than plainly stating 'checks whether a reputation record is portable across platforms'.

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 routing logic: a portability question about an agent identity setup belongs to wever_identity-portability-check, a memory export to wever_memory-export-check, a signed receipt to wever_receipt-passport, and this tool handles reputation-record portability. That is real alternative naming rather than inference. It stops short of stating when-not to use it for adjacent reputation siblings such as wever_reputation-record-check, so the routing is good but not exhaustive.

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