Prepare Change

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

Annotations only flag it as a non-read-only, non-destructive, non-idempotent open-world call; the description adds the critical facts an agent could not infer: no side effect is transmitted until commit, the return is a *signed* preview, a server-side env flag must be enabled, and human confirmation is required. This is exactly the behavioral context annotations cannot carry.

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?

Three dense sentences, front-loaded with the gating condition, and no filler. The opening clause ('Step 1 of 2 for what costs money or cannot be undone') is slightly telegraphic in grammar but still parses correctly and earns its brevity.

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?

Covers staging, side-effect posture, prerequisite flag, and the human-in-the-loop requirement, which is strong for a 12-parameter, no-output-schema tool. It omits how the signed preview is carried into telgea_commit_prepared_operation (a token/handle returned by the preview), which the agent needs to close the loop.

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 92%, so per-parameter meaning is already documented for kind, userId, numberId, portInId, countryCode, terminationDate, deleteUser, etc. The description only restates the enum of kinds (identical to the schema enum) and adds no guidance on the conditional field requirements or the `fields` object. Baseline 3 is correct.

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 verb and resource ('prepare' a change), enumerates the exact eight operation kinds it covers, and declares it is 'Step 1 of 2' which pairs it with telgea_commit_prepared_operation. An agent can tell immediately this is the preview stage, not the executor.

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?

Explicit trigger ('what costs money or cannot be undone'), explicit staging rule ('Step 1 of 2', 'nothing is sent'), explicit prerequisite ('Requires TELGEA_ENABLE_WRITES=true'), and explicit workflow instruction ('Show the preview and warnings to the user and get an explicit yes before committing'). Routing to the sibling commit tool is unambiguous.

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