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

Beyond the readOnly/idempotent/destructive annotations, the description discloses concrete behavioral traits: 'granularity day only', 'hour or minute returns unsupported_granularity', 'Non-whitelist project returns data_status=not_in_scope', the l2 field exclusions ('no tx_count/l1_fee_usd'), and 'No account access, no order placement or fund transfers. Not investment advice.' All of this is genuinely additive and consistent with the annotations.

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 description is front-loaded with the core purpose and contains zero wasted sentences—every clause about fields, sources, and exclusions is functional. However, it is a single dense run-on paragraph covering three variants; the lack of structural separation makes it harder to scan, and some implications (chain default derivation) are ambiguous in the paragraph form.

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?

Given an output schema exists and 100% schema coverage, the description is quite complete: it covers data sources, whitelist behavior, granularity constraints, error paths (unsupported_granularity, not_in_scope), and read-only caveats for all three metric groups. For an 8-parameter tool with variant behaviors per group, this is thorough, though the absence of explicit when-not-to-use guidance leaves minor room for improvement.

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% and every parameter already has a useful description, so the baseline is 3. The description adds real value on top by enumerating exact return fields per metric group (tps_avg_1d, active_addresses_1d, blob_cost_usd_1d, sequencer_revenue_usd_1d, stage_label; the btc_l2 whitelist stacks|rootstock|merlin|bob|bitlayer) and clarifying derived defaults (chain defaulting to ethereum/btc). It complements rather than repeats the schema.

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 specific verb+resource: 'Chain-level activity metrics' organized by metric_group, and enumerates three distinct variants (staking, l2, btc_l2) with concrete data sources (dwd_external_l2_metrics_daily_di, dwd_external_btc_protocol_di) and field lists. This level of specificity cleanly distinguishes it from siblings like get_bridge_metrics and get_defi_overview 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?

The description gives clear context about scope by mapping each metric_group to its domain (Ethereum staking, L2 ops, BTC L2 ecosystem) and explicitly notes granularity/limit/project are group-restricted, helping the agent configure calls correctly. It does not, however, explicitly name alternatives or state when not to use this tool versus the many platformmetrics/onchain siblings.

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