Agenda Intelligence MD

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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses critical behavioral traits: it does not retrieve sources and refuses calls with no evidence, it only grades evidence and names missing items, and it requires human review before commercial action. These details are not present in annotations and significantly help the agent understand side effects and limitations.

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 moderately long but highly informative, with each sentence contributing distinct value: purpose, verification details, required fields, behavioral constraints, usage alternative, and limitations. It is front-loaded with the core purpose and avoids redundancy, though it could be slightly more concise by combining related clauses.

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's complexity (nested request object, no output schema) and the provided annotations, the description is quite complete: it covers what it verifies, what it returns (payout allocations and missing evidence), required fields, when to use it, limitations, and the human review requirement. It also points to a full schema contract URL for deeper detail, so the agent has sufficient information to invoke it 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?

The input schema only describes the 'request' parameter and links to an external contract, while the tool description lists the required fields inside 'request' (escrow_id, deal_terms, specification, delivery_submission) and explains the verification criteria (hashes, schema, deadlines). This adds meaningful parameter context beyond the schema, though it does not detail each field's type or format.

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 explicitly states the tool's function: 'Deterministic dispute arbitration and delivery verification for Agent-to-Agent escrow transactions' and details what it verifies (SHA-256 hashes, JSON Schema compliance, contract deadlines) and what it calculates (binding payout allocations). It also differentiates itself by naming corridor_sanctions_assistant as an alternative starting point, making the purpose unmistakable.

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?

The description provides explicit usage guidance: 'With only a question and no evidence yet, start at corridor_sanctions_assistant' and lists exclusions ('no factual-truth verification, no legal, compliance, sanctions, or financial advice'). It also states that calls without evidence are refused, clarifying when not to invoke the tool.

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