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

Goes well beyond annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) by disclosing delivery channels (email / signed webhook), the auto-close lifecycle for tracked items, the API-key requirement, and a concrete cost model (rows past the first 10 per delivery cost credits per 100). This is the kind of billing and side-effect information an agent cannot infer from structured fields.

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 dense sentences with the core action front-loaded, followed by the track variant, then prerequisites and cost. Nearly every clause carries information; the parenthetical '(ZIPs, status, type, stacked)' is slightly compressed to the point of being terse.

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 10-parameter mutating setup tool with no output schema, the description covers delivery mechanics, auth, billing, and tracking lifecycle well. Gaps remain: what is returned on success (watch ID?), whether name is a label, and what the kinds values do, so it is strong but not complete.

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% across 10 parameters, so the description does real work: it maps zips/status/type/stacked to list filters, explains track as item keys and webhook_url as a signed endpoint, and implies cadence. But name, kinds, and the meaning of 'stacked' are never explained, and 'by email' has no corresponding parameter, leaving half the surface 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?

States a specific verb and resource: save a watch on one compliance list, with delivery of daily/weekly diffs. The 'Save a watch' framing clearly separates it from the read-side siblings (list_compliance_watches, get_compliance_changes), though it never names those alternatives 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?

Clear context: use this to be notified of changes on a recurring cadence rather than polling, and 'Pass track (item keys) to follow items one by one' gives explicit guidance on when to use the item-level mode. A prerequisite (API key) is stated. No explicit exclusions or counter-case instructions.

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