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

With no annotations, the description carries the full burden and does so well: it discloses suppression of low-volume rows with counts in `suppressed`, privacy guarantees (no actor id, IP, raw path, query string or timestamp), the caller_supplied marking, valid_until=window_end, and that receipt signing is additive and cannot lose the observation. It omits any auth/pricing requirement or failure modes.

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 purpose is front-loaded in the opening clause and nearly every sentence carries substantive information (thresholds, privacy, receipt behavior). It is a dense wall of run-on clauses, which slightly hurts scannability, but little is wasted.

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 no output schema and no annotations, the description compensates by explaining the row model, the `suppressed` object, referral `status` values (404/503), and key returned fields. It stops short of a full return-shape spec, but is adequate for correct invocation.

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 100%, so both `week` and `receipt` are already documented in the schema. The description largely restates these ('?week= picks the week containing a date; default is the current week', '?receipt=true for a signed Receipt v1.0'), adding only marginal framing over 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 first clause gives a specific verb+resource and scope: a 'weekly public aggregate of demand' covering only 'referral and ghost_referral' kinds. It is clear what is retrieved. However, it never explicitly distinguishes itself from the very similar siblings get_referral and get_demand_aggregate, so an agent must infer the boundary.

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?

It describes operating conditions (ISO week window, default to current week, n_threshold=3, optional receipt flag) but never states when to reach for this tool versus get_referral or get_demand_aggregate. Usage is implied by the semantics rather than routed explicitly.

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