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

With readOnlyHint=false and destructiveHint=false, the description still clearly discloses that this replaces a person's tags, that an empty list clears to 'No match', that rates/people views recompute immediately, and that the override persists across re-tags. This is rich behavioral context beyond what the annotations provide.

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?

The summary is front-loaded with the purpose, then follows with identity/the ID sources, parameter constraints, side effects, and persistence. Every sentence adds operational value, and the returns section is compact and useful.

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 persistent, state-changing override with no output schema, the description is thorough: it explains the return value, the empty-list clearing behavior, immediate recomputation, and the fact that a later re-tag will not overwrite the correction. Nothing needed to call it correctly appears to be missing.

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?

The input schema already has 100% description coverageasiatic. The description largely restates the tag_ids semantics and the sources for group_id/person_id, adding only minor workflow guidance about identifying the person first and passing corrected tag ids from the group's tags.

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 description states a specific verb and resource: it corrects/replaces the tags on one person for a segment group when the classifier is wrong. It distinguishes itself from message-classification and reply-outcome correction siblings by scoping to 'one person' and 'segment group' tags.

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?

It gives clear usage context: use this as the human-set override when the classifier got a person's tags wrongging. It also names the source queries for person_id and explains constraints for single-tag groups states an explicit when-condition but does not name alternatives like classify_segment_group or correct_message_classification.

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