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

Annotations are all false, so the description carries the burden. It adds useful behavioral context: cost per call (£5), compliance references (EU AI Act Art. 14, ISO 14064-3 lite), and what the call returns. It also states exclusions ('Not a carbon credit'). This goes beyond the false annotations and provides meaningful side-effect information.

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 four sentences, each adding distinct value: main action, return type, exclusions, and cost/compliance. It front-loads the primary purpose and avoids redundant wording, though the compliance list could be trimmed without losing core clarity.

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 two-parameter request tool with an output schema, the description covers key operational context: what it does, what it returns, cost, compliance, and what it is not. It does not mention failure behavior or rate limits, but these are minor given the tool's simplicity and the presence of an output schema.

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%, with both parameters already documented in the input schema. The description does not add additional meaning for project_id or claimed_ndvi_min beyond what the schema provides, so the baseline of 3 applies.

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 begins with a specific verb and resource ('Verify a carbon project's basic NDVI via Sentinel-2') and clarifies the return type ('signed Ed25519 NDVI attestation'). It explicitly distinguishes from full MRV by stating 'No Lean 4 proof' and 'Not a carbon credit', which helps differentiate it from the sibling tool request_mrv_report.

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 implies this is a lighter alternative ('Lite', 'No Lean 4 proof') but never explicitly says when to use this versus the full request_mrv_report. There is no stated precondition, when-not-to-use, or named alternative, leaving the choice to inference.

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