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

READ-ONLY is consistent with readOnlyHint=true, and the description goes well beyond annotations: numbers come from the data engine, not the LLM; each finding carries a payload of evidence; proposed_action is a pre-built tool call that must be executed ONLY after explicit user approval with a preview first; and org scoping (all outposts vs single venue) is spelled out. That approval-workflow disclosure is critical behavioral context an agent could not infer from the 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?

Front-loads the READ-ONLY guarantee and purpose, then rules, then usage, then scoping — a sensible order. It is dense and lengthy, but the rule glossary and approval workflow each carry weight for a multi-rule tool; the redundant restatement of default status (also in the schema) is minor waste.

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 4-param, no-output-schema tool, the description is complete: it explains the return shape (payload evidence, severity, proposed_action), the source of the data, filtering behaviour, and the downstream approval requirement. Nothing needed to call or act on it is missing.

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 75% (severity's enum lacks a description). The description compensates by explaining each rule_key value's meaning and confirming default status=open, adding real semantic value. It is docked slightly because it describes an account_id scoping parameter that does not appear in the input schema, which could mislead the agent about available filters.

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?

States a specific verb+resource (listing daily operational findings) and defines exactly what a finding is: a numerically-evidenced issue from the deterministic Vendooly engine, with severity and an optional proposed_action. It enumerates the five rule types, so the agent knows precisely what this tool surfaces and can separate it from catalogue/ad tools in the sibling set.

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?

Gives explicit trigger phrases ('che problemi ho?', 'cosa devo sistemare?', 'controlla il mio account') and positions it as the FIRST MOVE plus daily recap. However it never names or excludes the closest siblings (weekly_recap, diagnose_sales_drop, get_account_health), so the boundary against those alternatives is left to inference.

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