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

The description discloses key behavioral traits beyond the annotatiations: it is a lookup-only operation that never initiates a new third-party audit, and it depends on prior scans by the merchant. It also enumerates the specific output components (score, grade, hard-block status, protocol adoption). This adds significant value beyond the read-only and idempotent hints.

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?

Two sentences, each earning its place: the first states the purpose and output details, the second explains the precondition and non-behavior. The information is front-loaded and tightly packed without redundancy.

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?

For a simple one-parameter, read-only tool with no output schema, the description is complete. It explains the return values, the precondition, and that no new audit is triggered. It is sufficient for an agent to select and invoke the tool 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 schema already provides a good description of 'host' with an example, and coverage is 100%. The description adds the constraint that scores only exist for stores that have been scanned, which gives the parameter contextual validation. This goes beyond the schema's basic type description.

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 checks an AI agent's ability to buy on an e-commerce store and returns a deterministic readiness score with grade, hard-block status, and protocol adoption. It distinguishes itself from triggering a new audit, making its purpose specific. The verb 'Check' and resource 'host' are explicit.

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 clear context: scores exist only for stores that have been scanned, and this tool never triggers a new audit. This implies when to use it (for existing scans) and when not (for new audits), though it doesn't explicitly name alternatives like list_agent_ready_stores. This is strong guidance but falls short of fully contrasting with sibling tools.

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