compare_artifacts

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

With no annotations, the description carries the full burden and does well: it discloses exactly which aspects are compared (kind, axes, stamps, coordinates, data) and the exact tolerance rule |a - b| <= atol + rtol * |b|. It also pre-empts a likely confusion about non-deterministic ids across hardware. It does not state whether the result is a boolean or a detailed mismatch report, though an output schema exists to cover that.

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?

Two sentences, front-loaded with the core action and rationale, with no filler. The second sentence is dense with the comparison tuple and formula, which slightly impedes scanning but every clause earns its place.

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-parameter comparison tool with an output schema and no annotations, the description covers purpose, motivation for existing, comparison scope, and tolerance semantics. An agent has enough to invoke it correctly; the only omission is explicit identification of a/b as artifact ids and the parameter defaults, which is minor.

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%, so the description must compensate. It meaningfully explains atol and rtol via the tolerance formula, which is real value. However, it never states that 'a' and 'b' are artifact ids/hashes (only 'Ids are hashes' is mentioned in passing), nor the defaults of atol=0 and rtol=1e-9, leaving two of four parameters underspecified.

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 ('Check whether two artifacts agree numerically') and immediately scopes it to a concrete scenario ('the same step run on a laptop and on a cluster'). The second sentence distinguishes it from raw identity checking by explaining that artifact ids are hashes of exact bytes, so this tool does semantic/numeric comparison instead.

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 laptop-vs-cluster example gives a clear triggering context for when to reach for this tool. It does not name alternatives or state when-not to use it (e.g. versus inspect_artifact for single-artifact inspection), so the guidance is contextual rather than exhaustive.

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