Save a baseline snapshot

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

Annotations flag destructiveHint=true and idempotentHint=false, but the description never explains why saving a baseline is destructive — presumably it overwrites an existing baseline with the same name, which the agent needs to know before calling. It also says nothing about persistence (where snapshots are stored, whether they survive a restart) or whether the snapshot is captured immediately versus lazily.

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?

A single front-loaded sentence with a parenthetical example — no waste and the purpose leads. It is arguably too terse for a destructive, three-parameter write tool, but the brevity itself is not a structural flaw.

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 destructive write tool with no output schema and zero schema description coverage, the description covers only the happy-path purpose. Missing are overwrite semantics, permission or disk-space implications, what the tool returns (a name, an id?), and how the baseline relates to camera_compare's expected arguments.

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% for three parameters, so the description must compensate and largely does not. The example name 'door-closed' gives useful naming-convention guidance for the name parameter, but camera is undocumented (identifier format, whether it must come from list_cameras) and the quality enum's effect on the stored baseline is never mentioned.

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 gives a concrete verb+resource ('take a snapshot and keep it as a named reference') and names the consuming sibling, camera_compare, which separates it from the plain camera_snapshot tool. It stops short of explicitly contrasting with camera_snapshot, but the persistence intent ('keep it') is clear enough to pick the right tool.

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?

Usage is implied through the downstream tool reference ('for camera_compare'), which hints at a snapshot-then-compare workflow. There is no explicit statement of when not to use it, what happens if a baseline with that name already exists, or whether the baseline must be created before comparing.

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