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

Annotations only say readOnlyHint=false and destructiveHint=false, but the description adds substantial behavior: the correction REPLACES existing tags, recomputes group rates and message views immediately without re-classification, and persists past later re-tags so newly-added tags are not applied. These are non-obvious traits an agent must know.

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 prose is dense and front-loaded, leading with the core purpose before prerequisites and edge cases. It runs long, but nearly every sentence (persistence, recompute, empty-list clearing) carries actionable meaning, so little 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 4-required-param mutation tool with no output schema, the description covers identifiers, tag semantics, side effects, persistence, and even an inline returns block describing the confirmation dict — leaving nothing an agent needs 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?

Schema coverage is 100%, so baseline is 3, but the description adds genuine semantics beyond the schema: a single-tag comparison accepts at most one tag id and an empty list clears to 'No match'. It also reinforces that tag ids must come from the group's tags, tying parameters to the workflow.

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 — setting or correcting tags on one sent message within a tag group — and immediately scopes it as the 'human-set override' for a single (group, message), distinguishing it from sibling bulk classifiers like classify_message_tag_group.

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 explicit trigger conditions ('when the classifier got it wrong or skipped it') and names the sibling tools to source the required identifiers from (list_sent_messages, query_tagged_messages, list_message_tag_groups). It also states behavior for the edge case of clearing to 'No match'.

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