merge_topics

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

With no annotations, the description carries the full burden and does real work: it discloses which data is mutated (claims, topic notes, video links, search index) and that old names survive as aliases rather than being deleted, which is the key safety fact. It stops short of stating reversibility, idempotency, or the effect of a failed run.

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?

Two dense sentences plus an inline example, front-loaded with the operation and its shape; nothing repeats the schema. "Pause first" is terse to the point of being cryptic, but it is short enough that the efficiency outweighs the terseness.

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?

An output schema exists, so return values need no explanation, and the mutation surface is disclosed. But for a no-annotation, multi-entity rewriting operation, the description omits atomicity, error behavior, and the exact pause/resume procedure implied by "Pause first" — an agent could plausibly pause and never resume.

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 0% and the single `groups` parameter is an undescribed nested object of arrays, so the description must compensate. The JSON example successfully conveys the key/value shape, but it leaves a real ambiguity: whether the map key must already exist (rename vs. create-on-merge) or can be a brand-new canonical name, and whether one source name may appear in multiple groups.

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 compound verb+resource ("Rename/merge topics") and immediately grounds it in a concrete JSON mapping, so the direction of the merge (new name -> list of old names) is unambiguous. It is clearly distinct from sibling readers like list_topics and get_topic, though it never names them explicitly.

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?

"Only existing names are used" and "Pause first" give an eligibility constraint and a prerequisite, which points the agent toward the pause_brain sibling. However, it never names pause_brain or resume_brain, never says when to prefer this over get_topic/list_topics inspection first, and gives no when-not guidance.

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