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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false), so the description carries real weight and does: it discloses the dry-run default, what the preview reports (would-add, duplicates skipped, rejected, plan-limit effect), the 500 cap, and that confirm:true persists. It stops short of stating partial-failure behavior or required permissions, so it is strong but not exhaustive.

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 compact blocks — behavior, when-to-use, when-not-to-use — with the dry-run semantics front-loaded in the first sentence. No filler, and the labeled structure makes scanning trivial.

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 batch mutation with no output schema, the description covers the critical unknowns: default is non-destructive preview, what the preview reports, the size cap, and the dedupe rule. What the saved response returns (e.g. created/skipped counts) is not described, a minor gap given no output schema exists.

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 67%, and the description compensates for the gaps that matter: it explains confirm's dry-run/save split and the 500-item ceiling, and clarifies the matching keys (email, then exact name) that govern duplicate handling. Nested item fields like ref, tags, and mobile are left to the schema, which is acceptable since they are self-evident.

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 (Adds) and resource (Clients), defines the domain term inline ("people the practice does MTD quarterly updates for"), and specifies the input form (pasted list) plus the dedupe rule (email, else exact name). An agent can distinguish this from update_client without opening either 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?

Explicit "Use this when" names the concrete scenarios (spreadsheet, accounting-software export, typed list), and "Not for: changing one Client (update_client)" names the sibling alternative and the condition that selects it.

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