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

Annotations already declare non-read-only, non-destructive, non-idempotent. The description adds real behavioral substance beyond that: the operation fans out to every row carrying the word, and colliding with an existing word silently merges two categories into one. That merge side effect is exactly the kind of consequence annotations cannot express, and it is a notable omission that reversibility is not stated given destructiveHint=false.

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 first sentence is well front-loaded, but the closing 'Effects: category replaced on every row that carried it' restates it, and the framing 'Categories are the person's words ... one reasoned act rather than a re-review' is editorial padding that does not change how the tool is called.

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 three-parameter tool with no output schema and solid annotation coverage, the definition covers scope and the merge side effect adequately. It stops short of saying whether the rename can be undone or what happens to rules/reports referencing the old word, which matters for a workspace-wide mutation.

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 `from` and `to` are already documented. The description adds meaning to `to` by explaining that a value colliding with an existing word triggers a merge, but says nothing about the optional `reason` parameter or the accepted word format.

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 gives a specific verb-plus-resource with scope: change a category word across every row carrying it, as one atomic act. That is clearly distinguishable from the per-row sibling purch_tag_category, though the sibling is never named, so the agent must infer the distinction.

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 implies usage (rename when the vocabulary word itself changes rather than re-tagging rows) and discloses a key consequence: renaming onto an existing word merges the two categories. But it never states when to prefer purch_tag_category or purch_vocabulary instead, nor any preconditions.

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