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

Annotations declare readOnlyHint=true, openWorldHint=false, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context: it explains compute modes (server vs browser), transient processing (no storage/logging), and the deterministic nature (via execution_hash). However, it does not elaborate on what happens to data after processing beyond 'not stored', or clarify the return format beyond 'exports an AP2 artifact'. The description does not contradict annotations.

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 dense and front-loads key facts (purpose, compute behavior, privacy), but includes a long list of output feeds and a verification link that could be considered tangential for an agent deciding to call the tool. It is not overly verbose, but not every sentence earns its place; the feed list is useful context but may be better placed in annotations.

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 the complexity of the tool (4 params, nested objects, compute behavior, output artifact), the description covers important aspects: compute modes, transient processing, privacy constraints, and output artifact type. No output schema exists, so the description's mention of 'AP2 artifact' and 'execution_hash' helps fill that gap. The description is reasonably complete for an agent to understand what it does and how to invoke it.

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 descriptions cover all parameters (100% coverage), including detailed explanations for compute, parent_hashes, parent_tool_ids, and policy_parameters. The description adds little beyond that; it mentions 'compute:auto' default and browser delegation, but this is already in the schema. It does not add new semantic meaning to the parameters. Since schema coverage is high, baseline 3 is appropriate.

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 title and description clearly identify this as a comparator for agentic payments protocols, with a specific resource ('Agentic Payments Protocol Comparator'). The description distinguishes it from siblings by specifying its role as an OpenChainGraph compute node with routing policy and output feeds to related tools. It is less explicit about what exact comparison it performs (e.g., comparing features, costs, security), which could be inferred from the name and context.

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 context on compute modes and how inputs are handled, but it does not explicitly state when to use this tool versus alternatives like 'compare_agentic_payment_protocols' (a sibling with a similar name). There is no exclusion guidance or alternative recommendation. The output feed list hints at its downstream use but not at alternative tools for comparison tasks.

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