Create pipeline schedule variable

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true, so the description doesn't need to repeat those. However, the description adds the key behavioral detail: 'without returning its value'—which means the response likely omits the value, an important quirk for an agent to know. It also implies the operation is non-destructive, but doesn't clarify side effects like whether it overwrites an existing key (likely not, but not stated). Given annotations cover safety, the description adds decent context but misses potential errors or validation requirements.

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 a single sentence, front-loaded with the verb and resource. It includes a meaningful behavioral clause. No wordiness, no repetition of schema content. It's appropriately minimal and efficient.

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?

This is a create operation (mutation) with 5 parameters, 4 required, no output schema (though has one, but it's not provided in the context), and low schema coverage. The description covers the basic purpose and the 'no return value' quirk, but doesn't cover parameter details, error conditions, or its relation to the pipeline schedule lifecycle. Given sibling tools like update/delete exist, a note on idempotency (e.g., what happens if key exists) would help. It's adequate for a simple create but incomplete for a tool with many required parameters and no param descriptions.

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?

The schema description coverage is only 20%: only 'project' has a description. The description adds no parameter semantics beyond the tool's name. Four required parameters (project, pipeline_schedule_id, key, value) have no added meaning: what is 'key'? What does 'value' accept? What does 'variable_type' default to? The description's 'without returning its value' hints at the 'value' parameter but doesn't explain it. With such low coverage, the description should compensate, and it fails to do so.

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 clearly states the action (create a variable) and the resource (pipeline schedule variable). It also adds a specific behavioral detail—it doesn't return the value—which distinguishes it from similar tools like update_pipeline_schedule_variable or get_project_ci_variable. The verb 'create' + resource 'pipeline schedule variable' is specific and unambiguous.

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?

The description implies usage: you'd use this to add a new variable to a pipeline schedule. But it offers no explicit guidance on when to use this vs. update_pipeline_schedule_variable, or whether it requires an existing pipeline schedule. No alternative tools are named, and the 'without returning its value' hint is a behavior note, not a usage condition. It's adequate but lacks explicit context on prerequisites or exclusions.

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