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

Annotations already cover read-only, idempotent and non-destructive, so the description's added value is the domain semantics: missing coverage errors instead of returning zero, top rankings cannot span buckets, amount maxima do not reveal tx hashes, and no native security or anomaly decisions. These are real, non-obvious traits beyond the annotations. It still says nothing about result shape or row limits, which matters since there is no output schema.

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 operation, then a prerequisite, then caveats; no filler sentences. A few clauses are telegraphic to the point of ambiguity ('Inspect integrity and consumer_policy'), which costs a bit of clarity.

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?

A 14-parameter tool with no output schema needs more: the description covers pitfalls and prerequisites but leaves every parameter's meaning and the returned structure undocumented. The caveats are the right kind of content, but coverage is insufficient for a query tool this wide.

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% across 14 parameters, so the description carries the full explanatory burden and does not meet it. Nothing is said about metric selection, period/start_date/end_date interaction, grain, rollup, compare, group_by, dimension_filter syntax, or the 'schema' field. Only the vague phrase 'comparable UTC windows' gestures at compare behavior.

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 ('Execute a validated read-only native Fetch query') and enumerates the analytical shapes supported (sums, extrema, weighted means, groupings, rollups, UTC windows). It is clearly the query-execution counterpart to analytics_catalog, though that differentiation is implied rather than explicit.

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 an explicit prerequisite ('Read analytics_catalog first') and names the sibling, plus concrete constraints on when a result is invalid ('Top rankings cannot be combined across buckets'). It does not give an explicit when-not-to-use case or point to the security/anomaly siblings by name.

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