usage_read

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the bar is lower; the description still adds useful context — workspace-wide vs per-agent scope, the 400-day cap, and agency-only gating on clients_analytics. It restates 'Read only' (redundant with readOnlyHint) and says nothing about rate limits or response size beyond what the schema's mode already covers.

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 purpose, then time-range rules, then an action-by-action inventory in the same order as the enum — dense and largely waste-free. It is a single wall of prose rather than listed items, which makes a ten-action dispatcher harder to scan than it needs to be.

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?

With ten actions, 13 parameters and no output schema, the description carries the return-value burden and does so by naming the actual metrics per action plus availability constraints (agency only) and the pointers for analytics handled elsewhere. Practically everything needed to select an action and call it correctly is present.

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 92% so the baseline is 3, but the action enum has no description in the schema at all and the description supplies all of it — defining the meaning and return shape of each of the ten values. It also documents cross-parameter interactions the schema only hints at (logsPage implies includeLogs, includePerAgent defaults true, topN default differs by action).

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, credits and activity') and then enumerates all ten actions with concrete payload fields ('creditsCharged and creditsConsumed, input/output tokens per model...'). It also explicitly names the boundaries against siblings (WhatsApp/SMS analytics live in whatsapp_numbers_read / sms_numbers_read, voice in call_logs_read, KB quota in get_kb_quota), so an agent can separate it from neighbours 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?

Strong routing guidance: 'overview ... start here for "how is my usage"' tells the agent the default entry point, and out-of-scope data is redirected to four named sibling tools. It does not, however, distinguish this tool's agent_usage action from the sibling get_agent_usage / get_agent_usage_bulk, which is the one obvious overlap left unexplained.

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