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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool is clearly non-destructive. The description adds significant behavioral context: it explains that inputs are processed transiently and not stored/logged/retained, mandates synthetic or anonymised inputs only, and describes the output artifact (AP2 with execution_hash) and offline verification receipt. This goes beyond annotations without contradicting them. One minor gap: it doesn't explicitly state idempotency, but that's already in 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 but not excessively long, covering many operational aspects. It front-loads the purpose and then details compute modes, privacy, and provenance. Every sentence adds value, but the mention of the FV-status URL and specific artifact links could be seen as extra details that may be better placed in additional metadata, so a slight deduction from 5.

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 tool's complexity (4 params, nested objects, compute mode enums) and no output schema, the description is quite complete: it explains default behavior, execution modes, privacy implications, and offline verification. However, it doesn't provide examples of typical input values or explain the exact format of parent_hashes beyond 'execution_hash values', which could be ambiguous. Also, it doesn't mention error conditions or potential limitations. These are minor gaps given the rich context provided.

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%, so the schema documents all parameters. The description adds value by clarifying that compute:'auto' is default and that gpu:true nodes always delegate, which is not fully captured in the schema. It also explains the semantics of parent_hashes and parent_tool_ids as chaining inputs, which aligns with 'chain provenance' but is somewhat implicit. Since coverage is high, baseline is 3, but the description compensates by clarifying execution modes and input handling, making it a 4.

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 verifies timestamp attestations within the OpenChainGraph compute node framework, specifying its deterministic nature and compliance mandate. It differentiates from siblings by detailing compute modes and chaining behavior, but it doesn't explicitly name sibling tools or contrast with them, so a slight deduction.

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 implicitly guides usage by explaining when to use compute:'auto' vs 'browser' and when inputs are computed server-side, which helps an agent decide between execution modes. However, it doesn't explicitly state when to prefer this tool over alternatives like verify_execution_hash or anchor_stamp, nor does it mention non-use cases. The sibling context is huge, so more explicit routing would earn a 5.

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