Verify the cryptographic integrity of an agent's breadcrumb chain. Returns { is_valid, block_count, issues[] } plus epoch Merkle roots. A valid chain proves no audit records have been tampered with.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_pk | No | Ed25519 public key (64 hex chars). Omit for own agent. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and provides useful behavioral detail: it lists the exact return shape ({ is_valid, block_count, issues[] } plus epoch Merkle roots) and explains the semantic meaning of a valid chain. It does not address permissions or side effects, but verification is inherently non-destructive and the return semantics add clarity.
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, front-loaded with the core action, and packed with necessary detail (return shape and guarantee). No wasted words.
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?
The tool has one optional parameter and no output schema; the description compensates by explaining the return fields and the validity guarantee. It is sufficient for selecting and invoking the tool, though it could be more explicit about when to prefer it over sibling verification-like tools.
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 coverage is 100% and the parameter agent_pk is fully described in the schema as an Ed25519 public key with an omit-for-own-agent note. The description adds no additional parameter context, so the baseline of 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 description uses the specific verb 'Verify' with the resource 'an agent's breadcrumb chain' and states cryptographic integrity. It clearly distinguishes from sibling tools like gns_get_compliance_report and gns_get_trust_score by focusing on tamper-evidence verification.
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 clearly implies this tool is for checking integrity of a breadcrumb chain, giving context for when it would be used. It does not explicitly name alternatives or exclusions, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct purpose within its domain: gns_* tools handle compliance reporting, trust scoring, epoch rolling, and chain verification, while perception_* tools handle tile fetching, classification, embedding, and weather queries. Even similar tools like gns_get_compliance_report and gns_get_trust_score are clearly differentiated by scope (full report vs quick score).
The gns_* tools follow a consistent verb_noun pattern (get_compliance_report, get_trust_score, roll_epoch, verify_chain), but perception_* tools mix styles: perception_fetch_tile is verb_noun, perception_classify and perception_embed are just verbs, and perception_weather is a noun. The two prefixes (gns_ vs perception_) also introduce a split, though each group is internally readable.
Eight tools is well-scoped for a server that combines two related functions: AI-powered earth observation and cryptographic compliance auditing. Each tool serves a distinct role and there are no redundant utilities, making the count feel intentional and complete.
The core workflows are covered: fetch a tile, classify it, embed it (though not yet implemented), and weather queries for context, with a full compliance trail via breadcrumbs, epochs, and verification. The only notable gap is that perception_embed is explicitly marked as not implemented, leaving a placeholder in the tool surface, but the rest of the pipeline is functional.