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

The description adds genuinely non-obvious behavior beyond the annotations: the tag is auto-created when absent and re-attaching is a no-op, which tells an agent that retries are safe. However, that no-op claim sits in tension with the declared idempotentHint: false, so the two signals disagree about whether a repeat call is safe to retry.

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, front-loaded with the action, and the most load-bearing fact (auto-creation) arrives early rather than buried. "Attach a tag. Attach by name." is slightly redundant but costs little.

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 two-parameter mutation with no output schema and no annotations covering semantics, the definition covers the key side effect but omits what the call returns (the created tag? the association?) and what happens if the contact id does not exist. Adequate, 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 coverage is 50%: name has no description at all and id is only "Numeric id." "Attach by name" usefully establishes that name is the tag's name rather than its id, but the description never says what id identifies (contact vs. tag), leaving the more ambiguous parameter unresolved.

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?

"Attach a tag" states a specific verb and resource, and "The tag is created if it does not exist" implicitly separates it from the sibling create_tag (which would be a separate step) and from untag_contact. It never names a sibling explicitly, so an agent must infer the boundaries rather than being told them.

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 auto-create sentence gives useful implied guidance: you do not need to call create_tag first before attaching. Beyond that there is no stated when-to-use, no exclusion against create_tag/untag_contact, and no note on prerequisites such as the contact existing.

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