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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety bar is low, yet the description adds substantial behavior: bulk responses use a {bulk, operation, summary, results} envelope with per-Riddle entries, individual failures (no edit permission, foreign-project tagId) are isolated and do not stop other entries, and untagging the last carrier silently deletes the tag unless a question bank still uses it. That is real disclosure of destructive side effects beyond the annotation.

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?

Purpose is front-loaded and every clause carries information, but it is delivered as one very dense multi-clause paragraph with nested em-dashes, which makes scanning harder than necessary. Slightly tighter segmentation would improve it without losing content.

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?

There is no output schema, and the description compensates by describing return values (the tag plus all of the Riddle's tags; the bulk envelope shape), error semantics, permission gating, and the absence of a projectId parameter. Nothing an agent needs to call this correctly is 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 the baseline is 3, but the description adds meaning the schema cannot express: tagId lives in exactly one project so it only works for that project's Riddles, whereas tagName is created per-Riddle-project and can span projects in one call. It also confirms the UUID/UUIDs mutual exclusion and the max-100 limit in prose.

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?

States a specific verb+resource (put/remove a tag on Riddles) with the key structural constraint (one assignment per Riddle, never the tag itself), and explicitly names siblings riddle_tag_list and riddle_tag_delete to distinguish scope. An agent can separate this from riddle_tag_delete without opening either schema.

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?

Gives explicit when-to-use per action ('add' creates the tag in each Riddle's own project if absent; 'remove' creates nothing and errors on a missing tag) plus when-not and alternatives (riddle_tag_list for reading labels, riddle_tag_delete for removing the tag itself). Also states the preconditions: only if the Riddle's origin.writableByThisKey is true.

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