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

The description is transparent about cascade tag deletion, the Riddle sharing behavior, and cleanup by questionBank_delete. However, it explicitly states that a tag 'is deleted from the project' when nothing uses it, which directly contradicts the annotation destructiveHint: false; an agent following the annotations could underestimate the actual side effects.

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 dense but efficient; every sentence carries unique information about the basic action, cascade deletion, shared Riddle behavior, or the template rejection. The main behavior is front-loaded in the first sentence, and the longer explanatory portion is justified by the tool's complex side effects.

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?

The description fully covers the non-obvious consequences of this tool: tags cascade-delete when unused, tags are shared with Riddles, and public template ids are rejected, so an agent can predict post-conditions without consulting other tools. It omits the return shape and behavior for already-removed tags, but the absence of an output schema and the strong coverage of dominating semantics makes this a minor gap.

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 tagId and questionBankId are already documented. The description adds value by explaining how the parameters fit into the broader tag lifecycle and by revealing a validity constraint—rejection for public template ids—that is absent from the schema.

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 opens with a specific verb-resource pair: 'Removes a tag from a question bank by tagId.' It states exactly what is removed, from where, and by what key, making it clearly distinguishable from siblings such as questionBank_addTag and questionBank_tagList.

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 provides useful context about the shared tag namespace with Riddles and the tag lifetime, plus an explicit exclusion rule: 'Rejected for a public template id, see questionBank_templateList.' It does not explicitly contrast itself with riddle_tag_remove or riddle_tag_delete, but the shared-tag explanation largely implies the relationship.

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