Homo Universalis — HU-DIAMOND v1.1 Cryptographic Verifier & AST Kintsugi MCP Server

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, but the description adds materially new behavior: zero-auth, stateless, free at 0.00 EUR, and pure arithmetic that invokes no LLM. It also discloses the exact call-count formula (9 per turn, plus 10 inquisition calls at round 4) and the price ranges per tier.

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?

Purpose is front-loaded in the first clause and every sentence carries information, so there is no filler. However, the final sentence is an extremely dense run-on that packs call-count math, tier pricing, and language behavior together, which makes it harder to scan than a short bulleted breakdown would be.

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 an output schema present, the description need not explain return values, and it still covers everything else an agent needs: safety profile, auth (none), cost (zero), what gets computed, and how each of the three parameters shifts the result. Nothing required to call it correctly 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 coverage is 100%, so the baseline is 3; the description earns a step up by giving concrete outcomes for parameter values – tier='supreme' maps to gemini-4-argon at 10,000–64,000 Seeds / 10.00–64.00 EUR, and lang localizes vertex role descriptions. Some of this (the rounds-to-call-count mapping) duplicates the schema text rather than adding to it.

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?

States a specific verb and resource – computing deterministic LLM call counts, token budgets, and EUR/Seed costs for 1 to 4 spiral turns of the 8-vertex Diamond Wheel orchestrator. It also names both siblings and what they do instead, so the agent can route without opening any 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?

Explicitly scopes use to pre-run estimation ("Use this tool only to estimate call volume and cost before launching a multi-agent run") and points to the two alternatives for auditing code and notarizing text. When-to-use and when-to-use-something-else are both stated.

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

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

Beyond the annotations, the description discloses zero-auth/stateless/free operation, sub-4 ms performance, the four checks run on every call, and what happens on Python syntax or AST violations (status becomes 'violation_detected' with line-level diagnostics while still returning a valid signed response). This is substantial behavioral context.

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 jargon-heavy, but it is front-loaded with the main purpose and proceeds into usage, behavior, and parameters without obvious filler. Some sentences are very long, which slightly reduces readability for an agent.

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 complex cryptographic and AST verification tool, the description covers the main checks, error behavior, parameter effects, auth/state properties, and sibling alternatives. An output schema is present, so it does not need to explain return values in detail.

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 already documents all three parameters, including the enum for lang and the detailed diag_active mapping. The description restates this information but adds little meaning beyond the schema.

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 specific verbs ('Audit', 'verify') and resources ('Python source code', '8-vertex Reed-Muller RM(1,3) cryptographic crucible') to state what the tool does. It explicitly distinguishes this tool from its siblings by naming verify_sovereign_shield_merkle and simulate_diamond_spiral_budget.

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 gives explicit when-to-use guidance: auditing Python code snippets in code_markdown or obtaining an ES256-signed crucible attestation. It also routes users to the correct sibling tools for Merkle notarization/PII purification and multi-agent cost estimation.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower, and the description still adds real value: zero-auth, stateless, free (0.00 EUR), always executes all four pillars, PII is redacted before hashing, and `cost_zero_stop=false` or `budget_b < 120` raises a law-violation flag. 'Notarize' could superficially read as a write, but the explicit 'stateless' wording resolves that against readOnlyHint=true.

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 purpose and usage routing are front-loaded, but the description becomes a dense comma-spliced run-on that restates the four pillars twice (once as a list, once as elaboration). It is informative but noticeably over-packed with jargon, costing parseability.

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 annotations covering the safety profile and an output schema present, the description supplies everything else an agent needs: auth model, statelessness, cost, which pillars always run, and the specific conditions that trigger violation flags. Nothing material is missing for correct invocation.

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%, so the baseline is 3, but the description adds meaning the schema lacks — notably the `budget_b < 120` violation threshold, the effect of `cost_zero_stop=false`, and that `lang` localizes all pillar reports. The text parameter's redaction-before-hashing behavior is also clarified.

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 opens with concrete verbs and resources: notarize text into an RFC 6962 Merkle audit tree, strip PII under Zero-Knowledge rules, and verify cognitive load limits. It also names both siblings and what each does, so an agent can distinguish this tool from `verify_diamond_crucible_and_ast` and `simulate_diamond_spiral_budget` without opening any 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 states explicit when-to-use conditions (notarizing text, purifying PII, auditing cognitive load/fair-share economics) and routes the agent to the two alternatives by naming them and their domains. The only minor gap is the absence of an explicit when-not-to-use exclusion, but the sibling routing largely covers that.

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