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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses the full result vocabulary (pass, blocked with four named reason codes, needs_human_review), what the response contains (claims found, what each bound to, a content_hash that approvals bind to), and the cost/latency profile ('Deterministic and free: no model call'). The content_hash-to-approval binding is exactly the kind of behavioral context annotations 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?

Three sentences, front-loaded with the trigger condition, then the binding rules, then the return contract. Every clause carries information an agent needs, and the ordering follows the order in which the agent must reason about the call.

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 correctly takes on the burden of describing statuses, claim results and content_hash, which it does well. For a nested, multi-branch tool it is nearly complete; the remaining gap is that the tolerance and must_be_user_authored parameters are left to the schema without explanation of their effect on the verdict.

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 nested claim object has several undocumented sub-fields, but the description compensates by explaining what a binding may rest on: a verified fact from alterlab_facts, a user-authored mark, a quoted source, or the limit fact capping a commitment. That meaningfully explains the fact/quote/user_authored/limit branches. It does not explain the tolerance enum values (exact, currency, round_down_only) or what must_be_user_authored does to the run.

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 names a specific action (submit content with a claim binding per checkable statement) and a specific resource (the content object plus its claims), and it positions the tool in a workflow relative to alterlab_facts. An agent can distinguish it from sibling tools like alterlab_hands_answer or alterlab_policy_evaluate without opening the schema.

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 gives an explicit trigger: before writing a message, email, post or free-text form answer for the user, submit it here. It also clarifies the negative case implicitly ('Narrative with no checkable claim passes'), so an agent knows a check with no claims is not a failure. It stops short of naming an explicit alternative tool to use instead in any situation.

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