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

All annotations are false and carry no safety profile, so the description bears the full disclosure burden. It adds substantial value: discloses the £150 per-call cost, the non-certificate legal status, the returned attestation format, and the compliance regime. An agent is clearly warned this is a paid, state-changing request (readOnlyHint=false), matching the 'request' verb in the name.

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?

Four sentences, zero waste. Core purpose is front-loaded in the first sentence, then output type, then compliance, then the dual-cost/legal disclaimer packed efficiently into the final sentence. Nothing redundant — every clause earns its place.

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?

An output schema exists, so return format is documented elsewhere. The description covers purpose, method, output, proof mechanism, compliance context, cost, and legal exclusions. Minor gaps — prerequisites, rate limits, and error/queuing behavior for the paid request — exist, but the description is rich enough for an agent to invoke correctly.

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 each parameter is well-documented with examples, constraints, and the NDVI range already enforced. The description adds no parameter-level detail beyond the schema — the Lean 4 verification mechanics for claimed_ndvi_min are already present in the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Verify'), the resource ('carbon project's MRV claim'), the method (Sentinel-2 and MWCM-Oh), and the exact output (signed Ed25519 attestation with Lean 4 proof hash). These details differentiate it from sibling verification tools like verify_biodiversity and verify_site_certification, and the 'Not a carbon credit certificate' disclaimer prevents confusion with credit-related tools like issue_agent_attestation.

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?

Provides implied usage context through compliance references (EU AI Act Art. 14, ISO 14064-3) and a practical cost signal (£150 per call), but never names sibling alternatives or states explicit when-to-use/when-not-to-use conditions. The 'Not a carbon credit certificate' disclaimer is a weak negative constraint, not real routing guidance.

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