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

Annotations already declare readOnlyHint/idempotentHint, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the two return shapes (index/message vs. stepIndex/messageTmpl), retention of graph next/condition and X sendIf, and the warning to 'Preserve those fields in a full replacement.' These are context the annotations cannot convey.

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?

Three front-loaded sentences: the first enumerates returned fields, the second distinguishes the two modes, the third gives the preservation caution. The field enumeration is dense but each sentence carries distinct information, with no filler.

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 2-param, no-output-schema, read-only tool, the description covers return shape, the two read modes, and the editing caveat. Combined with the schema-provided workspaceId note, an agent has enough to call it correctly; only explicit sibling routing is missing.

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 only 50%: workspaceId is described in the schema, but sequenceId has no schema description. The description compensates by explaining exactly what sequenceId unlocks (full editable stepIndex/messageTmpl shape and exact revision), adding meaning beyond the raw UUID type.

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 name/verb 'list_sequences' plus the opening 'Sequences with executionModel, steps, approval state, status, and exact enrolled-lead counts' makes clear this returns sequence resources and their fields. It also distinguishes the two read modes (compact list vs. full editable shape). It does not, however, explicitly differentiate itself from sequence-related siblings like save_sequence_draft or set_sequence_status.

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?

It gives specific guidance for the sequenceId parameter ('pass sequenceId to read the full editable ... shape and exact revision before editing'), which is a real usage cue. But it offers no when-not-to-use and never names alternatives among the many sibling sequence tools, leaving the agent to infer the tool's place in the workflow.

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