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

Annotations only declare it is a non-read-only, non-destructive, non-open-world write. The description adds far more: creation is immediate and org-wide (visible to every station and flow), it can be plan-gated with an error that should be surfaced rather than retried, names are normalized to kebab-case, and the table is synced offline to stations. It also flags a confirmation requirement for unintended persistence.

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?

Front-loads the core action and then layers constraints, so the important guidance appears early. It is dense and somewhat run-on (multiple clauses per sentence, some restatement of the kebab-case rule already in the schema), but nearly every sentence carries a distinct operational instruction rather than 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 write tool with no output schema, the description covers the full lifecycle an agent needs: reuse checks, blueprint-collision avoidance, org-wide scope, offline behavior, plan/permission failure handling, and credential exclusion. Nothing material to calling it correctly is omitted.

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 only 50%, and the description adds meaning for the two required params ("name + typed columns", kebab-case normalization) and how generated code reads/writes rows. However, hubToken and description are never mentioned, and the field type enum / reference-linkage semantics are left entirely to the schema, so it does not fully compensate for the coverage gap.

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?

Opens with a specific verb+resource ("Create a new custom data table") and immediately scopes it with the schema shape (name + typed columns). It is trivially distinguishable from siblings like flow_update_custom_table, flow_list_custom_tables, and flow_request_secret, which the description names outright.

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?

Explicitly states when to use it ("USE THIS for any data the app must keep — loyalty stamps, waitlists, bookings, inventory logs") and when not to (credentials → request_secret). It routes the agent to list_custom_tables for reuse and search_blueprints to avoid duplicating tables a blueprint already provisions, with the precise failure mode ("a lookalike would sit dead") spelled out.

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