figure_library_archive_project_figure

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

Annotations establish a non-read-only, non-idempotent, non-destructive profile. The description adds genuine behavioral context beyond that: it discloses validation behavior ('returns integrity issues instead of treating incomplete archives as complete') and the execution responsibility model ('Host reports execution; SFL never runs scripts'). It stops short of covering auth, concurrency/revision handling, or failure semantics.

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 snapshot scope is front-loaded in sentence one, and the remaining sentences are short and dense with no filler. Slightly prescriptive about archive contents in a way that overlaps what the schema should carry, but still efficient.

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 4-required-parameter tool with a large nested object, no output schema, and 0% parameter documentation, the description leaves major gaps. It mentions integrity issues as a return concept but does not explain the parameters an agent must supply or the revision conflict behavior.

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% across four required and deeply nested parameters, so the description carries the full burden and largely fails it. It gestures at content semantics ('real plotting data', 'distinguish raw experiments from analysis tables', 'truthful sources') that loosely map to artifact roles and source fields, but figureId and, critically, expectedRevision (optimistic-concurrency token) go completely unexplained.

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 concrete verb ('Snapshot') and resource ('figure files under its working directory') with a scoping constraint ('only the explicitly listed'). It is reasonably distinguishable from the plan/apply and check siblings, though it never names an alternative to further sharpen the boundary.

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?

There is no explicit when-to-use, when-not-to, or alternative-tool guidance. The phrase 'only the explicitly listed figure files' implies a scope constraint but gives the agent no rule for choosing this over archival-adjacent siblings like check_project_figure or apply_project_figures.

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