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

Goes well beyond the annotations: annotations say destructive=true/idempotent=true, but the description explains that nothing is deleted, that the row merely drops out of ranking/planning reads, that a repeat archive is not an error and keeps the original archivedAt, that hadMeasuredMetrics/hadBrief/linkage are preserved, and that the effect is fully reversible via add_topics. This is rich, non-obvious behavioral disclosure that the structured fields cannot carry.

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?

Front-loaded with the one-line purpose before expanding into behavior. It is long, but nearly every sentence carries distinct, decision-relevant information (idempotency, reversibility, return fields, error case), with only mild redundancy around 'nothing is deleted' vs. the metric-preservation detail.

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?

With no output schema, the description proactively documents the response surface (alreadyArchived, archivedAt retention, hadMeasuredMetrics, hadBrief, articlePostId, and the topic-not-found degradation). Combined with the reversibility and idempotency notes, an agent has everything needed to call and interpret this tool correctly.

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 only 50% and the undocumented 'topic' param carries the important semantics; the description supplies them by clarifying it accepts either a term or a topicId. It does not add much to workspaceId, which the schema already documents, so it falls short of a 5.

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 precise verb+resource: 'Retire one topic-bank question by term or topicId.' The agent immediately knows what is being acted on (a topic-bank question) and how it is identified, which distinguishes it from sibling tools like archive_post or merge_topics.

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 clear operational context — it disappears from the reads that rank, plan, dedupe and re-measure, is reversible by re-adding via add_topics, and degrades with topic-not-found. It names add_topics as the undo path but never explicitly frames when an agent should archive rather than merge_topics or list_topics-first.

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