policy / evaluate

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description adds meaningful policy semantics beyond that: 'fail-closed', 'reads allowed, writes denied', and explicitly not equivalent to signer authorization. It does not explain return behavior or edge cases, but the annotations carry the safety profile.

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 description is a single compact sentence that front-loads the key policy constraint. It is efficient and avoids waste, though its terseness contributes to ambiguity elsewhere. It could still be slightly better structured by separating the exclusion from the core behavior.

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?

The tool is simple in shape—two required parameters, no output schema—but the description omits both parameter semantics and any explanation of what a successful evaluation returns. With no schema descriptions to fall back on, the description should do more to explain how 'action' and 'chain_id' drive the policy result. The high-level policy statement is not enough for correct invocation.

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 input schema has 0% description coverage and the description says nothing about the two required parameters, 'action' and 'chain_id'. It does not explain what kinds of actions are valid, how chain_id affects evaluation, or whether values are constrained. An agent cannot rely on the description to understand parameter meaning.

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 says this is a 'fail-closed policy demonstration' with reads allowed and writes denied, which gives some sense of the resource and policy semantics. However, 'demonstration' is vague and the exact operation—evaluating an action against a chain-specific policy—is not stated clearly. It distinguishes itself from signer authorization, but not from other siblings.

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 only usage guidance is a negative exclusion: 'not signer authorization.' There is no statement of when to call this tool, what it should be used for, or which sibling tools are alternatives. An agent still has to infer whether this is for testing policy behavior or for real authorization decisions.

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