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

With annotations only providing idempotentHint=false and destructiveHint=false, the description takes on the burden of explaining mutation side effects. It does well: re-tagging changes nothing, untagging the last carrier deletes the tag unless a question bank uses it, errors are reported per-entry without stopping others. This is rich, useful behavioral detail beyond the schema.

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 description is information-dense but quite long and somewhat winding, mixing multiple behaviors and edge cases in a single block. It front-loads the core action and alternatives, but the latter half is a wall of text that could be tightened with clearer segmentation.

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 complex tool with 5 parameters, 100% schema coverage, and no output schema, the description is remarkably complete. It covers return formats (tag plus all tags, bulk envelope with per-entry errors), failure modes, and the absence of projectId. Some details like the exact UUID format are left to the schema, but the overall context is well covered.

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 schema already documents parameters well. The description still adds valuable semantics: tagName is created in the Riddle's own project on add, tagId only works for that project's Riddles, and UUIDs supports bulk operations. This goes beyond mere schema descriptions, though the schema already handles the basics, so a 4 is appropriate.

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 clearly states the tool adds or removes a tag on Riddles via an 'action', and differentiates itself by naming sibling tools (riddle_tag_list, riddle_tag_delete). While the verb is somewhat split ('puts on or takes off'), the core purpose is evident and distinct from siblings.

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 description explains when to use this tool ('add' or 'remove'), contrasts it with reading labels and deleting tags, and covers key usage nuances like spanning projects, re-tagging, and error cases. It doesn't explicitly state when to choose alternatives over this tool, so it loses one point.

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