Record an audited GHG inventory in a separate append-only chain. mass_g is exact integer grams; content and factor-pack digests are bare lowercase SHA-256 hex. Idempotent on inventory_id.
| Name | Required | Description | Default |
|---|---|---|---|
| mass_g | Yes | ||
| agent_id | Yes | ||
| source_ids | No | ||
| inventory_id | Yes | ||
| content_digest | Yes | ||
| factor_pack_digest | Yes | ||
| factor_pack_version | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it discloses critical behaviors: append-only chain (immutability), idempotency on inventory_id, and exact format for mass and digests. It does not address permissions or error conditions, but the disclosed traits are substantial.
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 two sentences, front-loaded with the purpose, followed by constraints. 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 description covers core purpose and key constraints but omits several parameter meanings. Given the 7-parameter schema and no annotations, it is not fully complete, though an output schema exists to describe return values.
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 has 0% description coverage, and the description adds meaning for mass_g (exact integer grams) and digests (bare lowercase SHA-256 hex). However, it does not explain agent_id, inventory_id semantics beyond idempotency, factor_pack_version, or source_ids, leaving significant gaps.
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 records an audited GHG inventory in a separate append-only chain, using a specific verb and resource. This distinguishes it from sibling tools like record_work by emphasizing the append-only and audited nature.
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 does not provide explicit guidance on when to use this tool versus alternatives. It implies usage for recording inventory but does not mention sibling tools or exclusions.
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.
Most tools have clearly distinct purposes: recording work, recording inventory, listing, verifying, and attesting. 'attest' and 'carbon_receipt' are somewhat related but serve different functions (general attestation vs. carbon-specific receipt), so they are not easily confused.
The majority follow a verb_noun pattern (record_work, list_entries, verify_chain), but 'carbon_receipt' and 'footprint' are noun-only, and 'attest' is verb-only. This slight inconsistency in verb usage makes the pattern less predictable.
With 12 tools, the server is well-scoped for a compute ledger and carbon accounting domain. Each tool covers a distinct concern—recording, querying, verifying, and summarizing—without redundancy.
The surface covers the full lifecycle: recording compute work and inventory, retrieving and listing data, verifying chains and attestations, and generating summaries. No obvious gaps exist for the stated domain.