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

With no annotations, the description carries the full burden and does disclose meaningful traits: the handle is single-use, expires (default 1h), legacy columns auto-map, and each staging path returns upload_handle. It omits auth/permission requirements and size or validation limits, so it is strong but not exhaustive.

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?

Dense but well-structured: the 'When:' condition is front-loaded, and the A/B/C/D enumeration makes the branching scannable. It is longer than most definitions but every clause carries actionable content; only the terse parentheticals border on clutter.

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?

Given six parameters, zero schema coverage, and an existing output schema (so return values need no explanation), the description supplies the intake conditions, all staging paths, the auto-mapping behavior, the handle lifecycle, and the exact next call. An agent has everything needed to stage rows and proceed.

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 0%, so the description must compensate, and it does explain csv_file, csv_text (with the newline/JSON-encoding warning), assignments (appendable via upload_handle), and ttl_seconds indirectly via the 1h expiry note. guidance_handle is never mentioned, leaving one of six parameters undocumented.

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?

States a specific verb (stage/upload) on a specific resource (part-to-territory assignment rows or a legacy spreadsheet) and explicitly names its role in a workflow. It clearly distinguishes itself from direct_build by framing itself as the staging step that feeds assignments_handle into direct_build.

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?

Opens with an explicit 'When:' condition, names the alternative (inline in direct_build), enumerates four concrete staging methods (A csv_file, B csv_text, C assignments, D HTTP POST), and states the required follow-up call. Nothing about when to use it vs. alternatives is left to inference.

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