submit_change_for_approval

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

With no annotations, the description carries full behavioral disclosure. It states the state transition (to Assess), the side effect (creates an approval record), and explicit failure conditions (Change Model governance, sysapproval_approver direct inserts). This is notably transparent, even if it doesn't cover reversibility or permissions. The only minor gap is the lack of mention about return values or success behavior.

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: the first front-loads the main action and effect, the second adds a warning note. No redundant filler, and the structure is efficient. It loses a point only because the note, while important, is slightly tangential to the core action.

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 description covers the core action, side effects, and known failure modes, but omits the purpose of approval_comments and any expectations about the success response. For a simple two-parameter tool, this is decent, yet the missing parameter info creates a real gap that an agent must resolve through inference or trial.

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 describes only one of two parameters (change_id), and the description adds no clarification about approval_comments – its purpose, format, or whether it's used to populate the approval record. Since the description could easily have explained approval_comments but didn't, it fails to compensate for the 50% schema coverage. The agent must guess what to pass for approval_comments.

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 specific verb and resource: 'Submit a change request for approval', and describes the immediate effects (sets state to Assess, creates an approval record). This differentiates it from sibling tools like approve_change, which would handle an existing approval record. The purpose is 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 does not explicitly contrast with sibling tools such as approve_change or reject_change, nor does it state when this tool is preferred over them. It implies usage by naming its action, but leaves the agent to infer the decision boundary (e.g., 'use this to submit a new change, use approve_change to respond to an approval request'). No explicit exclusions or alternatives are given.

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