check_decisions

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

No annotations are supplied, so the description carries the full burden. The phrase 'without rewriting decisions' usefully implies decisions are not mutated, but it is silent on whether anything is written, what 'flag' produces, and whether a session must already exist. That is thin behavioral disclosure for a tool with zero annotation coverage.

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 a single front-loaded sentence with no filler, which is structurally clean. However, the brevity comes at the cost of under-specification rather than economical communication.

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?

For a two-parameter tool with no annotations and no output schema, the description should explain what a 'flag' looks like in the response and how the decision/evidence matching works. Neither is present, leaving the agent unable to predict the result of a call.

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% for two parameters, and the description only obliquely gestures at changed_files via 'changed ... evidence'. Nothing explains what session_id does, that it defaults to empty, or whether an empty value scopes to a default session.

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 verb 'Flag' and object 'changed or missing evidence' give a rough sense of intent, but the core resource, decisions, is only implied by the tool name rather than the prose. It does not differentiate itself from siblings such as record_decision or get_review_memory, so an agent must infer that this cross-checks recorded decisions against a set of files.

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?

There is no when-to-use guidance, no prerequisites, and no mention of any alternative tool. The agent is left to guess whether this should run before a review, after files change, or in place of record_review_outcome.

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