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

Annotations already declare destructiveHint=true, non-idempotent, non-read-only, so the safety bar is lower. The description adds real context beyond them: it can add and remove in one call, and via '(all: true)' it can mutate everyone matching a search, segment or product — a blast-radius disclosure that matters for a destructive tool.

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?

A single front-loaded sentence; the verb and resource lead and every clause earns its place by naming a targeting mode. It is slightly dense as one run-on sentence with a trailing parenthetical, but there is 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 eight-parameter, zero-required, destructive mutation tool with no output schema, the description gives a good selector overview but omits safety-critical guidance: that all:true with no filters tags the entire contact list, and that a call must meaningfully include add and/or remove. These are the exact cases an agent could get wrong.

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 the schema already documents all eight parameters, including limits ('up to 20') and the meaning of all/search/segmentId/productId. The description only restates the selector set as a narrative; it does not clarify whether add and remove can be combined, whether contactIds and emails may be mixed, or that at least one of add/remove should be supplied.

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 pair (adds/removes tags), the resource (contacts), and the scope (several at once), plus the three targeting modes. An agent can distinguish this bulk tagging operation from single-contact tools like update_contact or get_contact without opening the 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?

The phrase 'for several contacts at once' implies this is the bulk path versus per-contact updates, but no sibling is named and no when-not condition is given. Nothing tells the agent, for example, to prefer update_contact for a single contact or to use search_contacts first to build an id list.

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