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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description adds value beyond them: it discloses that only non-terminal transitions are permitted, that approval-only statuses are rejected outright, and that pipeline_stage_id resolves to a stage which is reported back in the response. No contradiction with annotations; the write behavior aligns with readOnlyHint=false.

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 sentences with no filler. The core constraint (direct, non-terminal, approval rejected) is front-loaded, and the optional pipeline_stage_id behavior is packed efficiently into the second sentence.

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 6-parameter mutation tool with no output schema, the description covers the central decision (which transitions are allowed) and the key optional parameter's effect. However, it does not explain what 'non-terminal' means in practical terms, nor the role of idempotency_key/request_id, and it relies on sibling naming for the approval-flow contrast.

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 carries the full burden for parameter meaning. It adds context only for pipeline_stage_id (targets a configured stage, resolved stage reported back). The required parameters application_id and status, plus reason, request_id, and idempotency_key, receive no semantic guidance beyond the raw schema.

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 action ('Directly write') on a specific resource ('non-terminal application transition') and clarifies scope by noting approval-only statuses are rejected. It distinguishes itself from the transition_bind/transition_preview siblings via the word 'Directly' and the approval rejection clause, though it doesn't name the alternatives explicitly.

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 rejection of approval-only statuses implies when NOT to use this tool, and the sibling set (transition_bind, transition_preview) suggests the alternative path, but this is left to inference. No explicit 'use X instead when approval is required' guidance is given.

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