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), so the bar is lower. The description adds genuine value beyond them: a privacy constraint ('Keep the receipt private') and polling behavior ('try again later'), though it omits any note on rate limits or eventual-consistency timing.

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 retrieval purpose, then the sibling routing, then the retry rule. Every sentence carries information, though the enumerated return-item list is slightly list-heavy for a single-parameter read tool.

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 usefully enumerates what can be returned, and annotations carry the safety profile, so an agent has enough to call it correctly. Minor gaps remain around receipt format and polling cadence, but nothing essential 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 0% – receipt_id is documented only by a UUID regex pattern. The description references receipt_id and adds the semantic that it is a private credential, but does not explain the expected format or where it comes from, so it only partially compensates for the coverage 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?

The description uses a specific verb ('Retrieve') and enumerates the exact resource contents it returns (proposed scope, price offer, payment details, operator decision, research response), keyed by receipt_id. It also distinguishes itself from the sibling respond_to_research_offer by naming it and its role, so an agent can separate the read tool from the action tool without opening either 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?

It explicitly routes the agent: use respond_to_research_offer to confirm/correct a scope or accept/decline a quote, i.e. the when-not-this-tool condition. It also gives the retry rule ('If no response is available, try again later'), leaving nothing to inference.

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