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

With annotations already covering the safety profile (readOnly, idempotent, non-destructive, closed-world), the description goes further and discloses real limitations: 'Recorded settlement is not revalidated on chain' and unmeasured cohort/regret metrics. That caveat-load is genuinely useful for interpreting results, though it stops short of describing pagination, error behavior, or what an empty dispatch returns.

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?

Front-loaded with the purpose and the return shape, and the teletype-style negative list compresses several exclusions into one sentence. It is dense and jargon-heavy ('exact-version', 'micro-USDC'), which costs some readability, but little is redundant.

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?

No output schema exists, so the description appropriately enumerates the return contents (bounded sample counts, citation hit rate, calibration bands, integer micro-USDC cost) plus the limits on those values. For a single-param, read-only tool this is close to complete, missing only error/empty-case behavior.

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 0%, so the description carries the burden, and it does add meaning by requiring an existing dispatch ID and forbidding a URL. However, it does not convey the identifier's regex constraints, length limits, or format beyond that single restriction, so it only partially compensates.

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 ('Read a public dispatch's retained exact-version BUY/citation/payment observations'), so the agent knows the operation and the data domain. It does not name a sibling tool, but the exclusion list ('No research, paid read, current-source backfill...') implicitly separates it from `research`. Clear, though sibling differentiation is left to inference rather than stated.

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?

'Use an existing dispatch ID, never a URL' is a concrete usage constraint, and the negative list scopes out adjacent activities (research, paid read, backfill). It never names a specific alternative tool to prefer, so it falls short of explicit when-to-use/alternative routing.

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