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

Goes well beyond the annotations by disclosing cost ('one fixed get_asset credit tariff per successful batch'), sampling limits (0-5 posts per asset, default 3, 2 for 17-20 assets, at most 50 total), non-exhaustiveness, absence of retention slots/cursors, per-item not_found semantics, and 'no upstream provider calls'. These are the behavioral facts an agent needs and none are derivable from the structured fields.

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 verb/resource/return shape and the sibling comparison, then facts in priority order. It is dense and packs several clauses (caps, sampling caveat, retention, result-handling advice) into a short block, with the trailing 'Retain full results in program state...' sentence the only mild overreach.

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?

For a 13-parameter, nested-input tool with no output schema, the description covers batch scope, cost, sampling bounds, partial-failure behavior, and when to use a narrower sibling. Filter-parameter semantics are delegated to a mostly-decent schema, so the definition is complete enough without being exhaustive.

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?

With 62% schema coverage the schema carries much of the load, but the description adds value the schema cannot: posts_per_asset defaults (3, dropping to 2 for 17-20 assets) and the 50-post aggregate cap, neither of which appears in the schema. Other filters (chain_ids, asset_type, evidence_class) rely on schema descriptions, so it isn't exhaustive.

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 (read) and resource (1 to 20 selected coins) plus exactly what is returned: dated identity, market-cap fields, whole-window activity, and a bounded newest post sample. It explicitly distinguishes itself from the single-item sibling ('Prefer this to a burst of individual get_asset calls'), so an agent can route without opening a 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?

Gives explicit when-to-use (batch of 1-20 assets), when-not (deeper selected evidence uses get_asset/get_posts), and a configuration shortcut (posts_per_asset=0 when only identity and counts are needed). Both the alternative tool and the condition that selects it are named.

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