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

Beyond the annotations, it discloses the exact billing contract (2 credits, charged only after a non-empty answer, free on refusal/error), the absence of an idempotency key ('Each call is a new answer and a new charge'), and the fallback behaviour where audit probability is missing (p = 1, labelled capacity_upper_bound_p1). It also explains how marginal inputs are surfaced (recommended-default slash fractions flagged with range, structural screens reported), which is far richer than readOnlyHint/destructiveHint/idempotentHint 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?

Every sentence carries load — pricing, theorem, input sourcing, fallbacks, scope limits — with no filler. The one structural flaw is front-loading: the billing preamble comes before the statement of what the tool computes, so an agent skimming the first clause learns the price before the purpose.

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 values needn't be described, and the description supplies everything else a caller needs: cost, invocation auth, input sourcing rules, refusal and unavailability behaviour, labelling conventions, and the ceiling-versus-verdict caveat. For a paid, non-idempotent compute tool this is complete.

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; the description earns above that by explaining that inputs are 'the network's published protocol parameters… each returned with the URL it was read from and the date it was last confirmed' and by defining the refusal semantics that govern the symbol argument's viability. It does not add per-parameter syntax (e.g. case sensitivity for tickers) beyond the schema's examples.

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 precise computational object — 'the left-hand side of Theorem 1 in Qazi (2026, arXiv:2608.12576), the enforcement capacity p * (lambda*S + delta*min Phi)' — with its unit and its interpretation as 'the largest per-audit deterrence ratio a network's slashing and probation can support.' No sibling tool produces this quantity, so an agent can distinguish it without opening any 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 states explicit when-not conditions: networks without sourced parameters 'are answered unavailable and not charged,' unsourced stake or slash inputs are 'refused, never defaulted,' and parameters not re-confirmed within 60 days are refused. It also clarifies the scope limit ('A ceiling, not a verdict… no incentive-compatibility answer is given'). What's missing is routing to alternatives — it never says to use find_networks or get_network first to confirm a ticker exists or to discover which networks have sourced parameters.

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