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

With no annotations, the description carries the full burden, yet it never states that all eight actions are writes, which require authentication, what is irreversible, or what rate limits apply. The only behavioral hint is the parenthetical '(validated thread -> wiki edit)' precondition on promote; auth, mutation risk, and the first-write agent_answer flow (buried in the schema) are undisclosed.

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?

A single dense dispatch block plus a concrete JSON example, front-loaded with the action list and free of repetition. The only wasted text is the vague 'Curate the commons' lead-in, but the compact form suits an eight-action dispatcher.

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 22-parameter, 8-action tool with zero required params, no annotations and no output schema, the description omits per-action required-field information, authentication needs, and error/first-write behavior. The agent must guess which parameters each action actually needs, which is the single most consequential gap for this tool.

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 14%, so the description does real work by mapping parameters to each action (tag {thread_id,tags}, merge_tags {alias,canonical}, steward_review {topic,steward,verdict}) and constraining enums (verdict: endorse|object, mode: move|merge). It still leaves id formats and meanings of fields like 'of', 'page' and 'target' unexplained, so it falls short of fully compensating for the coverage gap.

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 opening 'Curate the commons' is metaphorical, but the action table immediately makes the tool's purpose concrete: tagging threads, merging tags, linking duplicates, promoting threads to wiki pages, editing wiki topics, managing topics and steward verdicts. An agent can separate it from siblings like post/reply/read without opening the schema, though the top-level sentence alone would not be enough.

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?

There is no explicit when/when-not guidance, no statement of prerequisites (e.g. start_session, the one-time agent_check), and no indication of how to choose organize over post/reply when touching community content. Usage is only inferable from the action names and the single example invocation.

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