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

The description and title ('Preview', 'nothing changed yet') clearly indicate a non-mutating preview operation, but the annotation readOnlyHint=false suggests the tool may modify state. This is a direct contradiction. Since annotations are meant to guide the agent on side effects, the mismatch is critical and the description provides no clarifying behavioral details (e.g., auth requirements, rate limits, what is computed in the preview).

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 two sentences with no redundant words. It front-loads the key constraint (approval-required only) and rejection of bind/direct targets, then adds the optional pipeline_stage_id detail. The structure is efficient, though the second sentence is slightly dense and could benefit from clearer separation.

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?

The tool has 7 parametershol, no output schema, and conflicting annotations. The description covers some scope restrictions but does not explain what the preview returns, the meaning of the other parameters, or any behavioral context (e.g., whether a preview has side effects, side-effects/approval flow, auth needs). It is insufficient for an agent to call this tool confidently beyond the basic restriction checks.

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?

With 0% schema description coverage, the description must compensate for the 7 parameters. It only adds meaning for pipeline_stage_id (mentions targeting a configured stage and status match) and implicitly touches status. The other parameters (reason, request_id, idempotency_key, employment_start_date, application_id) are not explained at all beyond the raw schema types and constraints, leaving the agent to guess their role in a preview context.

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 states a specific verb ('Preview'), a resource ('application transitions'), and a clear scope ('approval-required only'). It explicitly rejects bind fields and direct-write targets, which distinguishes it from the sibling tools 'yardstick_applications_transition_bind' and 'yardstick_applications_transition_direct'. The title reinforces that nothing changes yet, making the tool's role 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 says the tool is for approval-required transitions only and that bind/direct targets are rejected, which gives a clear when-not-to-use condition. It also specifies when to optionally provide pipeline_stage_id and the status constraint. However, it does not explicitly name the alternative tools (e.g., transition_bind, transition_direct) for cases that need binding or direct writes, leaving some inference to the agent.

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