check_evidence_packet

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

With no annotations provided, the description carries the full burden. It clearly states the tool is deterministic and local-text only, and explicitly lists what it returns (broken references, quote mismatches, etc.). It also clearly states what it does not do. This is strong behavioral disclosure, though it could add details on side effects (but it's read-only, which is implicit from local-text only). Score 4, not 5, because it doesn't explicitly state idempotency or error handling, but it's very transparent.

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?

The description is two sentences, with the first sentence front-loading the purpose and usage condition. The second sentence lists return types and exclusions concisely. Every clause earns its place, and it's neither verbose nor missing information.

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?

Given the tool has only one parameter with a nested structure, the description references get_schema for the full contract, which covers the parameter semantics. The output is described in terms of return values (packet_complete, etc.) and the exclusions are clear. There's no output schema, but the description lists the key output types. The tool is complex but the description covers everything an agent needs to decide whether to call it and what to expect.

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 description coverage is 100%, so baseline is 3. The description adds value by explaining the purpose of the packet_json parameter (claims plus complete source texts) and points to get_schema for the full contract. This goes beyond just naming the parameter, so it earns a 4.

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 clearly states the tool checks a caller-provided evidence packet before human review, with specific verbs and resource. It distinguishes itself from siblings by listing its deterministic scope and what it does NOT do, which helps an agent differentiate it from tools like verify_claims or validate_evidence.

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?

Explicitly says 'Use when an AI output declares claims, source IDs, optional verbatim quotes, and the full supplied source text.' This gives a concrete trigger condition. It also lists exclusions ('does not retrieve sources, score source authority, assess factual truth, or authorize an action'), which helps an agent decide against using it for those purposes. However, it doesn't name specific sibling tools as alternatives, but the exclusions are enough to route correctly.

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