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

Annotations already provide readOnlyHint: true, and the description reinforces this with 'Read-only — it never writes.' Beyond that, it discloses detailed routing behavior: rows without a matching rule are skipped unless auto-create is opted in, __ignore__ rules yield 'ignored' status, and CSV mode returns a signed download_url. This adds substantial behavioral context not covered by annotations or schema.

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?

The description is dense but every sentence earns its place: purpose, routing semantics, read-only note, use case, filters, and CSV behavior. It is front-loaded with the core purpose. It could be slightly trimmed, but the structure is logical and the information density is high without being verbose.

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 tool with no output schema, the description thoroughly explains what the agent will receive: inline annotated rows or a download_url for CSV, with notes on routing, skip logic, and ignore rules. It covers filters, required connection_id, and model_id scope. There is no critical missing information an agent needs to call it correctly.

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 100%, so parameters are already well-documented. The description adds value by explaining the interaction of filters with CSV mode (filters don't apply) and the meaning of the routing annotations, which are not in the schema. It also clarifies that connection_id comes from layerz_list_integrations, which is extra context beyond the schema's generic description.

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 and resource: 'Read a data source's staged transactions', and immediately scopes it to API/csv imports via layerz_list_integrations. It distinguishes itself from sibling list tools (e.g., list_mappings, list_models) by the routing annotations and CSV export behavior, so an agent can tell it apart without opening the schema.

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 explicitly states when to use the tool: 'Use it to find rows that route nowhere before writing a mapping rule.' It also explains the CSV format alternative and that filters don't apply there. It does not explicitly state when not to use it or name alternatives, but the primary use case is clear and actionable.

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