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

Annotations already declare readOnly=true, idempotent=true, destructive=false, so the safety profile is covered; the description adds the meaningful domain context that these flags gate a VAT return. It also names the exact return fields (entity_type, entity_id, label, severity, title, detail), which matters because there is no output schema. It stops short of saying whether flags are deduplicated or whether severity orders results, but that is a modest gap.

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 purpose and the flag taxonomy come first, usage triggers second, return shape last — a sensible front-load. The enumeration of flag types is long but it earns its place by letting the agent match user vocabulary to this tool rather than a keyword search.

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 single-optional-parameter read tool with no output schema, the description supplies everything needed: scope, trigger conditions, the sibling it complements, and the shape of each returned flag. Nothing required to call it correctly is absent.

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?

There is only one optional parameter and the schema describes it fully, including the fallback behaviour ('leave it out to use the only company, or the default') and a pointer to list_companies. The description adds nothing about the company parameter, which is acceptable given 100% coverage — baseline 3.

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?

Specific verb plus resource ('List the entries Finn flagged'), scoped to pre-VAT-return review, and it enumerates the concrete flag categories (duplicate receipts, VAT on zero-rated purchases, personal-looking purchases). An agent can distinguish this from get_attention or get_reconciliation_status without opening any schema.

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?

Explicit trigger vocabulary ('flagged, suspect, duplicate or odd entries') maps directly onto user phrasing, and it names the sibling route — entries surfaced by get_attention that need a second look. That is a real when-to-use statement with an alternative, not just an implied context.

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