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

Adds real context beyond annotations: the results land in cellar history and feed lot data and reports, and InnoVint's API has no delete for this resource — which meaningfully qualifies the non-destructive annotation by warning that the write is effectively permanent. Auth requirements and rate limits are not covered, keeping it out of the top band.

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?

Front-loads the WRITE classification and the operation, with examples early rather than buried. It is a single dense paragraph where the trailing endpoint URL is the least essential element, but almost every clause carries actionable information.

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?

Covers a nested-array write tool well: required fields, the vessel-optional semantics, the slug lookup dependency, side effects and irreversibility. With no output schema, it could still say what the created action returns (id, timestamps), which is the remaining gap.

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 80%, so baseline is 3, but the description adds genuine meaning: the vessel_id/lot_id relationship (vessel-level versus lot composite), the required triple of analysis type slug, value and unit, and that the unit must match what InnoVint lists. Worked examples (pH 3.45, free SO2 28 mg/L) clarify the value/unit pairing.

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?

Opens with an explicit 'WRITE:' marker and a specific verb+resource: records analysis results as a new analysis action in the winery's InnoVint records. It is clearly distinguishable from sibling read tools such as innovint_list_analysis_actions and innovint_list_lot_analyses, and even names the exact endpoint.

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?

Gives concrete routing guidance: fetch the analysis type slug via innovint_list_analysis_types, and add a vessel for vessel-level results versus omitting it for a lot composite. It also states an important gating condition ('only call this when the numbers are confirmed'), though it does not contrast against sibling write/read alternatives.

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