contacts_anonymise

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

Goes well beyond the destructiveHint/idempotentHint annotations: discloses exactly what is erased (personal fields, activity bodies, merged duplicates), what is preserved (row ids, posted-document FKs, booked documents), the refusal conditions, and that there is 'no way back'. This is precisely the extra context the annotations cannot carry.

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-loaded with purpose, effect, then consequence, with a clear CONSEQUENCE marker at the end. It is dense but slightly over-written — the OR 958f Abs. 3 rationale for refusing on unpaid claims is restated at length and could be trimmed without losing meaning.

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 destructive, irreversible mutation with no output schema and near-zero schema documentation, the description covers scope, refusals, side effects and irreversibility thoroughly. Only the idempotencyKey contract and workspaceId scoping are left unaddressed.

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 0%, so the description must compensate. It clarifies contactId semantics well (must be the merge survivor; tombstones are refused), but workspaceId and idempotencyKey are never mentioned, leaving the required idempotency contract unexplained for a destructive tool.

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 ('Anonymise a contact') plus the legal trigger ('valid revDSG deletion request, bounded by OR 958f') and the concrete effect ('blanks the personal fields and redacts the activity bodies'). An agent can immediately distinguish this from archive_contact or contacts_merge.

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 clear preconditions ('on a valid revDSG deletion request') and explicit refusal cases (merge tombstone, live unsettled receivable/obligation with the status list). It also instructs to pass the SURVIVOR id, which implicitly routes merge handling elsewhere, but it never names a sibling alternative such as archive_contact or contacts_merge explicitly.

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