load_file_pipeline

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

Annotations already declare readOnlyHint=true, and the description usefully adds that 'Nothing is run' and that credentials are left as placeholders to be filled later. What it does not disclose is the fate of the generated template — whether a pipeline object is persisted (which would sit uneasily with readOnlyHint) or a spec/DDL string is merely returned — leaving a residual ambiguity an agent must resolve.

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?

Two tight sentences, front-loaded with the action and artifact type, then the scope constraint. 'on the cluster's side instead of through this computer' is a slightly wordy way to say server-side, but it earns its place by disambiguating the load location.

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 six-parameter tool with nested objects, zero schema coverage, and no output schema, the description says nothing about the arguments, the shape of the resulting template, or how credentials should be supplied. The behavioral half is adequate, but the parameter half is completely unaddressed, which is too thin for this complexity.

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% across six parameters (database, table, columns, options, file_name, create_sql), and the description explains none of them. It only hints obliquely that credential placeholders live somewhere in the options, so the schema-plus-description pair leaves every required argument semantically bare, including the nested columns array and free-form options object.

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 action and artifact: 'CREATE PIPELINE templates (S3 and Azure blob, credential placeholders)' that load a file server-side 'instead of through this computer'. This is clearly distinguishable from execution-oriented siblings like load_file_start or pipeline_monitor. It is slightly muddled about whether the template is returned as text or persisted, which keeps it off a 5.

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?

Gives an explicit selection condition: use this 'for files above the size limit', which implicitly excludes normal-size loads. However, it never names the alternative tool (e.g., load_file_start / load_file_target) for the under-limit case, so the agent must infer the sibling routing from the sibling list.

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