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

Beyond the annotations, the description discloses the ownership consequence ('the copy belongs to the company from then on: every member of that cabinet sees it, and deleting the personal capture does not remove it'), idempotency ('Attaching the same capture to the same entity twice is a no-op'), partial-failure reporting, and the full confirmation protocol with status='confirmation_required', action_id, and plan_token. This is exactly the behavioral context annotations cannot carry, and none of it contradicts readOnlyHint=false / destructiveHint=false.

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?

Purpose is front-loaded, then target modes, then side effects, then the confirmation flow — a logical progression with no filler sentences. It is dense and long, with quoted parameter names inline, but each clause conveys operational information rather than restating the name or title.

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 tells the agent what comes back ('what was attached and why the rest was refused') and, critically, that a successful-looking call returns a confirmation_required status requiring confirm_action. For a mutating, shared-visibility write tool, nothing essential to calling it correctly 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 only 33%, so the description must compensate, and it largely does: it defines the required combination of 'tenant' + 'entity_kind' + 'entity_ref', notes 'entity_title' is optional and ERP-only, and explains 'label_targets' as an alternative resolution mode rather than an additive flag. Remaining gaps are minor (the 200-item cap and the entity_kind values live only in the schema), so a 4 rather than a 5.

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?

The description opens with a precise verb and resource: 'Copy the caller's captures into a COMPANY cabinet, onto a CRM lead or an ERP organization / contact / project.' It enumerates the exact destination types matched by the entity_kind enum, so an agent can distinguish this from sibling intake tools like intake_assign_label or erp_attach_document without opening a 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?

It clearly states the two invocation modes — explicit 'capture_ids' plus target fields, or 'label_targets': true to resolve targets from client labels — and instructs the agent to confirm with the user which captures go where. It does not name alternative sibling tools or state exclusions, so it stops short of the top score, but the when-to-use context is unambiguous.

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