Remove contacts from a tag

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

The description materially enriches the generic annotations: it discloses that 'The work is queued, so a success response means it was accepted rather than finished' — asynchronous semantics not captured by any annotation — and precisely scopes the destruction: 'The tag itself and the contacts are not deleted,' which clarifies what destructiveHint=true actually destroys. No contradiction with readOnlyHint=false, idempotentHint=true, or destructiveHint=true.

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?

Four short sentences, purpose front-loaded, with each sentence earning its place: the bulk operation, the two targeting modes, the queued async behavior, and the precise destructive scope. No padding or repetition of the title. The only blemish is that the targeting-mode sentence references phantom parameters, but as a matter of conciseness the size and ordering are strong.

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 destructive, queued bulk operation with no output schema, the description covers the essential behavioral context (async acceptance semantics, what is and isn't deleted) — that is the strongest part. But it is incomplete in the dimension that matters most for invocation: the targeting parameters it instructs the agent to pass do not exist in the schema, there is no explanation of how contact_uuids should be obtained or formatted, and the required/optional relationship between contact_uuids and all_contacts is never clarified.

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 100%, which normally earns a baseline 3, but the two schema parameters (profileUuid, tagUuid) have only tautological descriptions ('Tag uuid parameter', 'Profile uuid parameter'). Worse, the description instructs passing contact_uuids and all_contacts — parameters that are entirely absent from the input schema. An agent reading both would not know whether to send a third parameter, making parameter semantics actively confusing rather than merely thin.

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 first sentence, 'Remove a tag from many contacts at once,' states a specific verb, resource (tag-contact associations), and scope ('many contacts') that distinguishes it from the single-contact sibling reach_removeAContactFromATagV1. Minor deduction: the title frames it as 'Remove contacts from a tag' while the description frames it as 'Remove a tag from many contacts' — functionally the same operation but worded in opposite directions.

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 description gives an explicit operational choice: 'Pass contact_uuids to target specific contacts, or all_contacts to target every contact in the profile.' This is genuine usage guidance. However, it never names sibling alternatives (e.g., using reach_removeAContactFromATagV1 for a single contact), and the two targeting parameters it instructs the agent to pass are absent from the input schema, which makes the guidance potentially misleading rather than purely helpful.

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