analyze

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

With no annotations provided, the description carries the full burden. It discloses several key behaviors: it returns a validated memo, or when ANTHROPIC_API_KEY is unset returns the assembled system_prompt for the host model to complete. It also clearly states limitations: 'No live source retrieval and no legal, compliance, financial, or investment advice.' This is valuable behavioral context beyond what any structured field would provide. A minor gap: it doesn't explicitly state whether the tool is a write operation or how it interacts with other components, but the description is quite thorough for a tool with one parameter.

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 a compact block of three sentences. The first sentence states purpose and scope. The second explains the request format and return behavior. The third lists limitations. Every sentence adds distinct value, no repetition, and key information is front-loaded. This is appropriately sized for the tool's complexity.

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 this tool has one nested parameter, no output schema, and no annotations, the description is quite complete. It covers what the tool does, when to use it, how the request is structured, the two possible return behaviors, and limitations. The only minor gap is that it doesn't detail the structure of the returned memo (output format) in depth, but since the request includes an output_format field and the sibling tools like validate_memo exist, an agent can infer the rest. This is solid coverage for a moderately complex 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?

Even though schema coverage is 100% and the request parameter is well-described in the schema (including an example and description), the description adds critical semantics: it explains that the request must match 'agenda-request.schema.json' and mentions the return behavior variation. It also references get_schema('agenda_request') for the full contract. This goes beyond the schema's basic property list, helping the agent understand how to construct the request properly. A 4 is appropriate since the schema already does heavy lifting, but the description adds meaningful guidance.

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's purpose: it generates an auditable strategic-risk memo from a structured Agenda request. It specifies the resource (Agenda request), the output (validated agenda-memo or system_prompt), and the scope (sanctions, regulatory, geopolitical, trade, corridor, or policy-risk questions). This distinguishes it from siblings like validate_memo, audit_claims, or specific risk tools (cis_secondary_sanctions_exposure) which serve different functions.

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 explicitly states when to use: 'Use for sanctions, regulatory, geopolitical, trade, corridor, or policy-risk questions where the agent needs a memo with assumptions, scenarios, evidence discipline, and regional routing.' It doesn't explicitly name alternatives or when-not-to-use, but the context is clear enough that an agent could infer it's for memo generation rather than validation or specific deep dives. A slight deduction for not naming specific sibling tools as alternatives.

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