core.compare

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

Annotations already cover safety (readOnlyHint, idempotentHint, openWorldHint=false), but the description adds real behavior: numeric fields yield delta_vs_baseline, non-numeric fields yield null, and scenarios are capped at 50 with unique-name constraints. That is substantive context beyond the structured fields.

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 core comparison mechanic is front-loaded, then field semantics, then the 50-scenario cap. It is dense but every sentence adds information; 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?

An output schema exists, so return-value shape is covered elsewhere, and the description still explains delta_vs_baseline and null-for-non-numeric semantics. Given nested scenario objects and four required parameters, the definition is nearly complete, with only the per-scenario object structure left implicit.

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 has to carry parameter meaning, and it does: tool is a read-only tool, base_arguments is the baseline run, scenarios are per-run overrides (max 50, unique names), and fields is a list of result paths with a concrete example (tax, breakdown.0.rate). The internal shape of each scenario object remains undocumented, keeping it from a 5.

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 states a specific verb (compare) and mechanism: it runs a read-only tool once with base_arguments as the baseline and again per scenario with overridden arguments. That is clearly distinguishable from sibling compute tools like core.add or core.calc, which return single values.

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?

It tells the agent this only applies to 'read-only' tools and frames the use case as scenario comparison, which implicitly excludes mutations. It does not name an explicit alternative or a when-not condition, so it stops short of a 5.

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