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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds substantive behavior: strict principal scoping ("Your principal's own history only, never another buyer's"), money as minor-unit strings, and the counter-intuitive second_price rule that cleared price sits above the claimed bid by design. Those are exactly the surprises an agent could otherwise misread as a data error.

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 purpose and scoping before the payoff details, and there is no filler. It is a single dense block though, so the caveats about minor units and second_price pricing would be easier to scan as separated 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?

With no output schema, the description carries the burden of explaining return shape and does so at section level (preferred_sellers with per-seller shares and standing, standing_terms, first_pass_history newest-first). A reader still has to infer exact field names and nesting, but for a read-only memory tool nothing needed to call it correctly 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?

Schema description coverage is 100%, including defaults and ranges for window_days and limit, so the schema already carries parameter meaning. The description restates the 180-day default and the per-capability-class grouping but adds no new syntax or interaction semantics for category or currency; baseline 3 applies.

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?

Names the side ("Buyer side"), the resource (accumulated procurement memory on Bitroad) and the value proposition ("a fresh agent instance does not start from zero"). It then enumerates the three return sections, so an agent can distinguish it from sibling read tools like auth_whoami or orders_list without inspecting 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?

Gives an explicit trigger ("Call it on your first turn") plus ordering relative to alternatives ("before services_search_listings or intents_post") and a guardrail on when there is nothing to read ("auth_whoami says when there is history to read"). This is the when/when-not/alternatives pattern in full.

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