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

Annotations already declare non-readonly, non-idempotent, non-destructive. The description adds meaningful behavioral context the annotations cannot: the interest value determines how the tag is bucketed in analytics, and tags are reused across campaigns for classification. It stops short of stating what happens on duplicate content or what the call returns (no output schema exists).

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 purpose followed by the two-mode distinction and the one non-obvious rule. Little filler; the analytics-bucket sentence does real work. Slightly dense but nothing is wasted.

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 create tool with non-destructive annotations and no output schema, the description covers purpose, both usage modes, naming conventions via schema, and the meaning of the enum. The main omissions are duplicate-tag behavior and confirmation of what is returned.

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%, so the baseline is 3; the description earns above baseline by giving `interest` a purpose the schema never states — it decides which bucket the tag feeds in reply-sentiment analytics. Combined with the schema's own content guidance (short label, ask the user for campaign names), an agent knows how to fill both parameters.

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?

Opens with a specific verb+resource ("Create a tag") and immediately explains what the tool's output participates in (reply-sentiment bucket selection). It doesn't explicitly contrast itself with tag_update or tag_list, so sibling differentiation is indirect, but the creation intent is unambiguous.

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?

Explicitly splits use into two jobs (reply classification vs. per-campaign lead identification) and tells the agent what to do in the second case: create a short campaign-specific tag with interest NEUTRAL rather than reusing an existing one. That is a real when/when-not instruction. No mention of checking tag_list first or of duplicate handling, so no perfect 5.

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