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

With annotations limited to readOnlyHint=false, idempotentHint=false, destructiveHint=false, the description adds meaningful behavioral context beyond them: 'validator-enforced' writes, 'versions the previous state' (aligning with destructiveHint=false), and the approval-retention rule. These are non-obvious side effects an agent must know before calling, though it could go further on revertability or downstream approval effects.

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 sentences, each carrying distinct payload: purpose, procedure plus behavior, and approval semantics. The full-object requirement is emphasized with capitalization of FULL, and no words are wasted.

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 write tool with a deeply nested profile schema and no output schema, the description covers the operational essentials: what to edit, how to obtain the current state, validator behavior, versioning, and the approval-status invariant. It doesn't describe the response format or error conditions, a minor gap given no output schema exists and the read tool is explicitly named.

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 75% (linkedinAccountId, profile, workspaceId described; readableSummary only has maxLength). The description reinforces the critical PUT-like semantic — send the whole profile back — and the profile param's own schema description echoes this read-edit-send pattern, which is substantive guidance beyond raw field definitions.

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 opens with a specific verb-resource pair — 'Edit a conversation voice profile's structured fields' — which unambiguously states the mutation action and target. It distinguishes itself from the read sibling by naming campaignstack_get_conversation_voice in the read-first instruction, and 'edit' vs 'extract' semantically separates it from extract_conversation_voice.

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 read-first directive ('read it first with campaignstack_get_conversation_voice') and the full-object requirement ('Send the FULL profile object back') give the agent an explicit procedure for correct invocation. It names the gatekeeper sibling that must precede it, though it doesn't state explicit when-not-to-use conditions or contrast with extract_conversation_voice.

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