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

Goes well beyond the annotations to disclose the full lifecycle: encrypted and private during review, two independent approvals, then potentially public with no further confirmation and irrevocable from readers. It also states auth prerequisites (WorkOS sign-in, agent must be linked to a user), that review agents may fetch public evidence URLs, and that there is no per-proposal human sign-off or subscription cost. This is exactly the context an agent needs before invoking an irreversible publish path that annotations only flag as destructiveHint=true.

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 correctly with the 'Use when...' trigger, but the body is a dense run-on of policy, auth, billing and URL-syntax rules in prose form. Statements like 'contributions are free with no subscription' and the WorkOS sign-in detail are tangential to selecting or invoking this tool, and the evidence-URL rule is duplicated from the schema's own uri description.

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 high-stakes, high-parameter-count, open-world tool with an output schema already defined, the description supplies the missing operational frame: prerequisites, review workflow, privacy window, irreversibility, and rights attestation. The remaining gap is the large set of undescribed enum parameters that determine what kind of proposal is created.

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?

With only 22% schema description coverage across 18 parameters, the description must compensate and it does so for a few: evidence URL format (HTTPS, no credentials/query/fragment, section identifiers in labels/notes), target_path binding for corrections, and the publication_rights attestation. However, many required parameters carry no meaning in either place - contribution_kind, domain, proposed_maturity, proposed_status, entry_kind, inference, reproduction, feedback_source and idempotency_key go unexplained, and several of those enums are non-obvious choices an agent must get right.

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?

Opens with a concrete usage condition: 'Use when task work produces a useful original reusable finding or concrete correction', which pins down the verb (propose) and the resource (shared community knowledge) plus the qualifying content type. It implicitly separates this from private_knowledge_create and community_search ('check existing corpus coverage', 'skip routine answers or duplicates') but never names those siblings, so differentiation requires inference.

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 both sides of the decision: propose when an original reusable finding or correction emerges, skip 'routine answers or duplicates', and check existing corpus coverage first. It also states gate conditions (corrections bind one exact target_path, rights basis restricted to agent_original or public_facts_only). It stops short of naming the alternative tools (community_search / community_get) an agent should call before proposing.

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