Core 1/4: Which mandates am I acting under?

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description still adds real context the annotations do not: the auth model (Bearer agent token or connector OAuth), the meaning of active=false (revoked, expired, sandbox closed), and that an empty result signals a missing credential. It does not cover pagination or result ordering, but those are minor here.

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 with the imperative "Call this first" and organized as scope → selection → handoff → failure case, so the highest-value instruction comes first. The field enumeration is dense but each field earns its place; only the run-on construction of the field list costs it a perfect score.

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?

An output schema exists, yet the description still explains the shape of the result and the semantics of active=false, which is exactly the judgment an agent needs when picking a mandate. Combined with the credential fallback behavior, nothing essential to correct invocation is missing.

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 single agent_token parameter has 0% schema description coverage, so the description must carry it — and it does, tying the token to the Authorization: Bearer header or connector OAuth sign-in and telling the agent to request it from the user when absent. It stops short of saying the parameter is optional and falls back to ambient credentials, which is the remaining gap.

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?

States precisely what is returned: the mandates the caller's credential was issued for, enumerating mandate_id, buyer, label, agent_id, and a rules summary. It also differentiates itself from the ordering siblings by naming request_quote and place_order as downstream consumers, so an agent can place it without opening any 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?

Explicit when-to-use ("Call this first"), explicit selection rule (pick the mandate matching the buyer the user names), explicit handoff (pass mandate_id to request_quote / place_order, agent_id may be omitted), and explicit failure handling (empty without credential → ask for token or mandate_id, never guess). Both the positive path and the no-alternative case are covered.

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