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

Annotations already declare destructiveHint=true and readOnlyHint=false, so mutation semantics are covered structurally. The description adds genuinely new behavior: edits apply to a single open draft, PII can be a warning, and new PII in agent or MCP saves is blocked. The PII sentence is somewhat terse and could be misread, but it is real context beyond the annotations.

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?

Purpose is front-loaded in the first sentence and the workflow sequence follows in logical order. However, the final sentence about PII and agent/MCP saves is compressed to the point of ambiguity and reads as a fragment relative to the rest.

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 three-parameter edit tool with no output schema, the definition covers what it changes (an open draft), where it fits in the edit-validate-save-test pipeline, and a notable failure mode (PII blocking). Missing only explicit note of irreversibility or what happens if the edge ID does not exist.

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 edgeId, workflowId, and versionLabel are already documented in the schema. The description adds no format, constraint, or default information (e.g. what the auto-generated version label means when versionLabel is omitted), so it merits only the baseline 3.

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 and resource: 'Delete an edge/connection from a workflow.' The scope (single edge, a workflow) is unambiguous and distinguishes it from workflow_delete, workflow_delete_node, and workflow_add_edge without needing the schema.

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 explicit when-to-use ('Use when editing a draft') and a when-not ('Do not use to activate or run a candidate'), plus a concrete follow-up sequence naming workflow_validate, workflow_guard, workflow_save_version, and workflow_test_run. It does not contrast directly with the nearest siblings such as workflow_delete_node or workflow_add_edge, which keeps it from a 5.

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