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

Beyond the readOnlyHint annotation, it discloses substantial behavior: small-count suppression (`count: null`, `suppressed: true`), the complementary-suppression rule that withholds the next-smallest cell to prevent recovery by subtraction (with the leftovers exception), and a privacy guarantee that no company or natural person is named. These are exactly the operational traits an agent needs and cannot get from the sparse schema or annotations.

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 sentence one, and the dense detail that follows is almost entirely load-bearing: register coverage, the `enriched` totals, cell `base` semantics, and suppression rules. It is long and packed, but each clause explains a field or a caveat rather than padding; only the parenthetical asides make it heavier than strictly necessary.

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, the description must carry the entire return-value burden, and it does: it defines every breakdown dimension, the `base` field for comparing mixes, the `unknown` buckets, the register-status enum, and the suppression behavior. Nothing an agent needs to correctly interpret a response appears to be missing.

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?

The tool takes no parameters, so the baseline is 4; there is no schema documentation to compete with. The description instead invests in defining the output cells (`entity_type`, `sector`, `size`, `region`, `company_status`, `lifetime`, `reactivation`, `leftovers`, `base`), which is valuable even though it is not, strictly, parameter semantics.

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 opening sentence names a specific verb and resource ('Get the company breakdown of the De-registered IDs') and anchors it to the `/v1/stats/deregistered` endpoint, making clear it is the company-breakdown companion to the aggregate tool. An agent can distinguish it from siblings like get_deregistered_stats and list_deregistered_ids. It stops short of explicitly naming the sibling to prefer for totals, keeping it at 4.

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?

'Same population, same daily rollup, same `deregistered` total' as `/v1/stats/deregistered` frames the relationship to the aggregate stats tool, implying this is the drill-down you pick when you need per-company-profile segmentation rather than totals. There are no parameters, so there is no filter-selection guidance to give, but the description never explicitly states the alternative or when-not to use it.

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