topos_begin_refactor

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

The description discloses that the only side effect is writing a snapshot record and that it returns a snapshot_id, but this contradicts the annotation idempotentHint=true. Writing a snapshot record implies each call creates a new side effect, so repeated calls would not be idempotent. This is an annotation contradiction.

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, front-loaded sentences: purpose plus side effect, return value plus follow-up workflow, and the specific usage condition. Every sentence earns its place with no filler.

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 purpose, side effect, return value, follow-up call, and the usage condition, which is quite complete for a 3-parameter tool with no output schema. However, the unresolved contradiction with idempotentHint leaves a behavioral gap around repeated calls.

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 100%, so the schema already provides meaning for all three parameters. The description adds only the filepath context and the workflow but does not explain preferences or gitnexus_dir beyond what the schema states.

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 it persists the file's current source as a baseline snapshot before editing, with a specific verb and resource. It also distinguishes itself from siblings like topos_assess_snapshot by framing this as the initial step in a refactor workflow.

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?

Explicitly provides a usage condition ('Use this when the baseline is not a committed git revision') and a concrete workflow: call this tool, edit the file, then call topos_assess_snapshot. This gives clear direction versus alternatives.

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