airtable-user-mcp

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

Annotations already indicate this is a destructive, non-readonly, non-idempotent operation. The description adds valuable behavioral context beyond annotations: the safety guard requiring both fieldId and expectedName, the dependency check that returns dependency info instead of deleting, and the force parameter override. It doesn't contradict annotations (destructiveHint=true aligns with 'delete'), but could mention more about error handling or response format.

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 efficiently structured in three sentences: first states the core purpose, second explains the safety mechanism and dependency check, third clarifies the force override. Every sentence adds essential information with zero wasted words, and it's front-loaded with the main action.

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 destructive tool with good annotations and full schema coverage, the description provides strong contextual completeness. It explains the safety mechanisms, dependency behavior, and force parameter significance. The main gap is lack of output schema information (what dependency info looks like, success/failure responses), but given annotations cover the safety profile and schema documents parameters well, this is a minor shortfall.

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 all parameters are documented in the schema. The description adds some semantic context: it explains the safety guard purpose of requiring both fieldId and expectedName, and clarifies that force=true overrides dependency checks. However, it doesn't provide additional meaning for appId or debug parameters beyond what the schema states.

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 specific action ('Delete a field from an Airtable table') with the resource identified ('field'). It distinguishes itself from sibling tools like 'delete_table' and 'delete_view' by specifying it operates on fields rather than tables or views, and from 'rename_field' or 'update_field_config' by focusing on deletion rather than modification.

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 provides explicit guidance on when to use this tool ('Delete a field') and when not to use it (if dependencies exist without force=true). It also implicitly suggests alternatives like checking dependencies first (implied by the dependency check behavior) and distinguishes from other deletion tools (delete_table, delete_view) by specifying the target resource.

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