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

Annotations cover safety (destructiveHint=false, idempotentHint=true, openWorldHint=false) but say nothing about cost; the description adds the credit model (counts free, first 10 rows free, then credits per 100 rows), which is material to how an agent should size `limit`. It also discloses an important interpretation limit ('off the list means the agency's data no longer lists the item'), a genuine behavioral caveat beyond the 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?

Three tight sentences, front-loaded with what the tool returns, followed by cost and the interpretation caveat. Minor awkwardness in the cost sentence ('Counts are free; the first 10 rows are free, then credits per 100 rows') but no filler.

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 an 8-parameter, no-output-schema tool, the description covers purpose, cost, and one semantic caveat but leaves result shape, pagination via offset, and the `until` window behavior unexplained. Adequate to invoke a simple call correctly, but not complete for a caller that needs to page or bound a date range.

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 50%: zip, kind, since and stacked are documented in-schema, while limit, until and offset are not. The description adds the default 7-day window for `since` (already in schema) and ties the pricing tiers loosely to `limit`, but gives no meaning for `until`, `offset`, or combined zip/kind/stacked usage, so the undocumented half stays undocumented.

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 description pairs a specific verb set (added, taken off, changed) with a specific resource (a compliance list) and names the data source ('the agency's own data'), which clearly separates it from get_compliance_items or list_compliance, which presumably return current state rather than deltas. It stops short of naming a sibling or stating the delta-vs-snapshot distinction explicitly.

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 context is implied by the default time window ('since a day (default the last 7 days)') and by the clarification that 'off the list' is not proof the work was done, which implies a caveat-sensitive use case. Nothing states when to prefer this over get_compliance_items/list_compliance, nor are prerequisites for the `list` values given.

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