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

The annotations only declare the safety profile (readOnly=false, idempotent=false, destructive=false, openWorld=false); the description goes well beyond that by disclosing the full execution pipeline — fetch flow, AI-merge reusing existing nodes, versioned snapshot labeled 'Added notes by AI agent', and transcript append. This is exactly the additive behavioral context the annotations cannot carry.

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?

It is a single dense sentence, front-loaded with the purpose and then the pipeline steps in execution order. Nearly every clause earns its place by describing a distinct side effect, though it is on the long side for one sentence.

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 multi-step, non-idempotent mutation with no output schema, the description supplies return values (new node and edge counts plus an open link) and side effects, so an agent can call it and interpret results. The one real gap is the absence of any disambiguation from the near-identical sibling 'notes_to_flow'.

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 100% for both parameters, so the schema already documents flow_id and text. The description only restates that text is follow-up notes merged into the flow and that flow_id must be existing, adding marginal meaning beyond the schema. Baseline 3 is appropriate.

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 states a specific verb and resource ('add new notes or transcript... to an existing flow') and even details the multi-step outcome (merge, snapshot, transcript append). It is clear what the tool does, but it never distinguishes itself from the very similarly named sibling 'notes_to_flow', leaving the agent unable to tell them apart from the text alone.

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?

Usage is only implied through the phrase 'from a follow-up call', which hints at the scenario but gives no explicit when-to-use, prerequisites, or when-not-to-use conditions. It names no alternative, so the agent must guess whether this or 'notes_to_flow'/'edit_flow' is the right choice.

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