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

Goes well beyond the readOnly/openWorld/destructive annotations: numbers come from the deterministic data engine not the LLM, each finding carries numeric payload, severity, and sometimes a pre-built proposed_action requiring explicit approval, and the list is org-scoped (all outposts vs a single venue via account_id) with default status=open.

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 'READ-ONLY' and the core purpose, and every clause (rules, approval workflow, scoping, usage) carries information. It is one dense paragraph though, and the long rule enumerations make it heavier than strictly necessary for scanability.

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?

With no output schema, the description still explains the finding structure (numeric payload, severity, proposed_action) and the full lifecycle, plus usage and scoping, so an agent has everything needed to call and interpret the tool. The only minor gap is the account_id/schema mismatch.

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?

Adds real meaning over the schema: it explains what each rule_key value detects and clarifies the status default and org-scoping behavior. However account_id is described as a filter while it is absent from the input schema, which adds a small ambiguity; severity enums are left to the schema.

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 (list daily operational findings produced by the deterministic Vendooly engine on the Data-Hub) and enumerates the exact rule set it returns, which no sibling (e.g. get_listing_issues, diagnose_sales_drop) duplicates. An agent can tell it apart from the ads_*, audit_*, and get_* siblings immediately.

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?

Explicitly designates it as the PRIMA MOSSA for 'che problemi ho?', 'cosa devo sistemare?', 'controlla il mio account', and the daily recap, and points to the corrective alternatives (update_listing, get_listing with included_data=issues). It also states the approval gate for proposed_action (execute only after explicit user approval, show preview first).

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