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

The description goes well beyond the readOnlyHint and openWorldHint annotations, explaining exactly how each dimension is evaluated, what verdicts mean, and edge cases like 'pass is never issued for a dimension that was not checked.' It also reveals fallback behavior and acceptance of both word-keyed and digit-keyed forms. This is richly transparent and lets an agent predict outcomes without having seen an invocation.

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?

This is a long description, but the length is earned by the complexity of the four-dimensional verification. The description is front-loaded with a one-sentence summary, then uses a clear pattern for the four dimensions and closes with verdict semantics and usage constraints. It could be tightened slightly, but every sentence is informative and the structure aids parsing.

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?

Given the absence of an output schema, the description supplies an explicit verdict enum and explains when each verdict is possible, including the caveat that a pass only occurs if the dimension was actually checked. It also covers input fallbacks, accepted forms, and uncertain cases like 'skipped if absent'. An agent has everything need to decide whether to call this tool and how to interpret its verdict.

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 parameters are already thoroughly documented. The tool description adds helpful high-level semantics — such as why chain, rider, probe_id, and topic_coordinate exist — and repeats the word/digit-keyed choice, but it does not materially extend what the input-schema descriptions already say. The schema carries the load here, matching the baseline expectation for a high-coverage definition.

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 opens with a specific directive — 'Deterministic arithmetic check on a SAND rider, v2' — making the operation and target unmistakable. It further breaks the check into four named dimensions (CHAIN, PROVENANCE, BALANCE, SQ) and lists possible verdicts, which fully conveys what the tool does.

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 description's opening sentence and involvement in the sand-v2 context make it clear this tool is for verifying SAND riders; the field-level detail implies when it is appropriate to invoke it. It also states the tool is non-enforcing, so the agent knows it is for judgment rather than enforcement. It does not name explicit exclusions or alternatives, but the unique verify purpose is obvious among the siblings.

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