policy_check

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

With no annotations, the description carries the behavioral burden. It usefully discloses policy caps, stop-signal finality, and that every check is receipted for ALLOW and DENY alike, but it does not clarify whether reset/report_stop mutate state, what permissions are needed, or how results are returned.

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 dense and front-loads the core purpose before policy details. It is a single long sentence, but nearly every clause carries substantive policy information rather than 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?

This is a complex tool with 8 parameters, a nested object, no annotations, and no output schema. The description explains the policy domain and caps well, but it leaves key invocation details and return behavior under-specified, which is a significant gap for correct use.

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 coverage is 0%, so the description must explain all 8 parameters. It clarifies the action values and implies the roles of week, counts, signal, and comment_text through policy rules, but adapter, account_id, owner_reset, and the nested counts object remain undocumented.

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 clearly identifies this as an engagement policy evaluator and lists the action values it handles (like, comment, report_stop, reset). It is specific about the policy domain, but it does not explicitly differentiate itself from nearby siblings such as approval_check or engagement_log.

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 action list implies the tool should be used to check engagement actions against policy before or during use. However, there is no explicit when-to-use guidance, no when-not-to-use guidance, and no named alternative for related checks such as approval_check.

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