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

Annotations already declare idempotentHint=true and destructiveHint=true; the description adds real context beyond them — the generation is immutable, and the server owns identities, hashes, tenant scope, receipts and publication state, so the caller must not supply those. It does not, however, explain why the operation is destructive or what prior state it supersedes.

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, front-loaded with the verb and resource, each adding a distinct piece of information (immutability, preconditions, server-owned state). No filler or repetition.

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 7-parameter, deeply nested, mutation-class tool with no output schema, the description covers purpose, immutability, idempotency and server-owned fields, which is solid. It is silent on failure behavior, publication receipts/return shape, and the destructive semantics flagged by annotations, leaving gaps for a call whose judgment union has strict server-enforced constraints.

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 29%, so the description must carry weight — it maps loosely to expectedPublication ('exact active publication bundle'), the evidence array ('exact evidence') and idempotencyKey. But several parameters (conversationId, schemaVersion, provenance, customerId, judgment union) get no explanatory treatment beyond the inline schema text.

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?

Specific verb (publish) plus a distinct resource (a new immutable Converra conversation-insight generation) scoped to an 'external teacher judgment'. It is distinguishable from siblings like regenerate_run_insights or record_review_decision, though it does not explicitly name the tool it replaces or complements.

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 states preconditions (exact active publication bundle, exact evidence, idempotency key) but never frames when to choose this over internal insight-writers, nor when not to call it. Usage is implied by the 'external teacher judgment' framing rather than stated.

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