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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the default multi-identity fan-out, and the fact that each invoice is tagged with {kind, id, label, vatMasked}. It does not say how many results come back by default or whether there is pagination beyond limit.

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 default-scope behavior is front-loaded before the per-parameter explanation, and every sentence carries information. The dense parenthetical asides (personal VAT plus companies they own or administer, the identity object) make the single paragraph slower to parse than necessary.

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 read-only, closed-world list tool with no output schema, the description supplies scope, filter semantics, value vocabularies, and the tag shape on returned records. The remaining unknowns — default page size, sorting, whether identity variants can be combined — are minor but real.

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%, so the description carries the full burden and largely does: identity ("all", "personal", "org:<organisationId>"), identities (array of personal/org ids), from/to (YYYY-MM-DD, inclusive), and limit (1–50) are all defined with formats and vocabularies the schema does not provide. The one omission is whether identity and identities are mutually exclusive or can be combined.

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 and resource — the signed-in person's past invoices — and names the concrete artifacts returned (PDF and document links via pdfUrl/documentUrl). The scope statement (all billing identities by default) makes the tool unambiguous, and no sibling in the list touches invoices, so confusion risk is minimal.

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 explains the default behavior ('without filters it covers every billing identity') and how each narrowing axis works, so an agent knows exactly what happens if it omits parameters. It never states a when-not-to-use case or names an alternative tool, but no sibling overlaps this capability, so the gap is small.

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