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

Beyond the readOnly/idempotent/closed-world annotations, the description adds substantive traits: the result is signed, the numeric part is deterministic while the interpretive part is conditional ("when armed"), the LLM saw only aggregates and never trace data, and the output is explicitly not a verdict. These are exactly the properties an agent can't get from the annotations or schema.

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?

It is short and free of padding, but the opening is front-loaded with metaphor ('Consult the oracle') rather than the concrete operation, and the single long sentence packs three distinct facts (determinism, conditional LLM layer, non-verdict caveat) into one dense clause.

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?

There is no output schema, so the description carries the full burden of describing return values; it names the two components (signed measurement, optional LLM interpretation) but not their shape, fields, or what happens when the interpretive layer is not armed. For a single-parameter read tool this is a plausible sketch but not complete.

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?

The single parameter vow_id has 0% schema description coverage, so the description must compensate, but it never names or characterizes the parameter—only alludes to 'a vow's trajectory.' Format, source, and whether an unknown id errors are all unstated.

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?

"Consult the oracle on a vow's trajectory" conveys that this retrieves a computed reading for a vow, and the second clause specifies the return content (a signed deterministic measurement plus optional LLM interpretation). However, the verb is metaphorical and the description never plainly says 'returns the current reading/score for the given vow', leaving an agent to infer the operation from the output description rather than a concrete action.

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?

No guidance on when to call this versus neighbors in a very large sibling set (read_ledger, verify, vows, vow_listing, witness_pledge). The only usable signal is implicit: it takes a vow_id, so it presumably applies after a vow exists, but no prerequisites, exclusions, or alternatives are stated.

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