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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description earns credit for adding non-obvious behavior instead: results are paginated, the cursor to continue is returned, and test-flagged events are silently excluded by default. The main remaining gap is that it doesn't state default ordering or what happens when filters match nothing.

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?

Dense and front-loaded: the read-only paginated nature comes first, filters second, the test-event default and return shape last. Every sentence carries information, with only the trailing 'Returns events + next_cursor' being mildly redundant against the existing output schema.

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 ten-parameter, zero-schema-described query tool this is close to sufficient: filters, value domains, date-range semantics, the test-event default, and pagination behavior are all covered. It is not fully complete because limit's maximum/meaning, filter combination logic (AND), and result ordering are unstated, and with no schema descriptions there is nowhere else for an agent to find them.

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 must carry the load, and it does for eight of ten parameters — meter, provider, channel, outcome (ok|error), consumer_class with its allowed values (internal|external|unknown), and the half-open ISO date range [since, until). The two it leaves undefined are limit and cursor, though 'paginated' plus 'next_cursor' gives enough to infer the cursor round-trip.

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 usage events') and adds scope qualifiers ('paginated, read-only'). It doesn't explicitly contrast itself with aggregate siblings like usage_summary or usage_timeseries, so the raw-events-vs-aggregation distinction is left implicit.

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?

Usage is implied by the resource type — this is the raw event-listing tool, so aggregation tools are presumably for rollups — but no alternative is named and no when-not-to-use guidance is given. The one piece of real routing guidance is the include_test default exclusion, which is behavioral rather than a selection rule between tools.

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